/home/linuxbuildslave/buildslaves/ailinux/ipc-prob-build-singularity-linux/build/tmpV19p8J /home/linuxbuildslave/buildslaves/ailinux/ipc-prob-build-singularity-linux/build/tmpV19p8J *************** RDDL-PARSER CALL WITH 600SEC *************** Parsing... Setting outcome pruning to 0.1 ...finished (0.00116396s). instantiating... Instantiating variables... ...finished (6.19888e-05) Instantiating CPFs... ...finished (0.000178814) Instantiating preconditions... ...finished (0.00089097) ...finished (0.00114822s). preprocessing... Preparing evaluatables... ...finished (0.000962019) Preparing actions... ...finished (0.000115156) Calculating CPF domain... ...finished (0.000406981) Finalizing evaluatables... ...finished (0.000113964) Computing determinization... ...finished (1.90735e-06) Determining task properties... ...finished (1.90735e-06) Preparing hash keys... ...finished (6.00815e-05) Precomputing evaluatables... ...finished (0.000941992) Calculating min and max reward... ...finished (2.14577e-06) ...finished (0.00264096s). analyzing task... Creating training set with 67 candidates. ...finished (0.028955s). writing output for instance crossing_traffic_demo_inst_mdp__1... ...finished (0.020839s). writing transition relations to json file... ...finished (0.00143313s). total time: 0.056226s RDDL-Parser took: 0.0636735s learning... THTS: learning... DD_Heuristic: learning [25s (0.125%)] with /home/linuxbuildslave/buildslaves/ailinux/ipc-prob-build-singularity-linux/build/tmpV19p8J/crossing_traffic_demo_inst_mdp__1.json... Horizon: 50 Round to dezimal: 2 { "actions": { "move(x1, y1) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s1 || s3] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x1, y2) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s0 || s2 || s4] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x1, y3) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s1 || s5] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x2, y1) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s0 || s4 || s6] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x2, y2) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s1 || s3 || s5 || s7] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x2, y3) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s2 || s4 || s8] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x3, y1) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s3 || s7] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x3, y2) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s4 || s6 || s8] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==0])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "move(x3, y3) ": { "Tc": "(0 - (0 - [!s8]))", "Tr": "([s5 || s7] * [!s8]) * (([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==1])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" }, "noop": { "Tc": "(0 - (0 - [!s8]))", "Tr": "(([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s0_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s0_primed==s0])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s1_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s1_primed==s1])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s2_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s2_primed==s2])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s3_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s3_primed==s3])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s4_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s4_primed==s4])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s5_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s5_primed==s5])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s6_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s6_primed==s6])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s7_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s7_primed==s7])) * ([[s1 && s9] || [s4 && s10] || [s7 && s11]] * ([s8_primed==0]) + [![[s1 && s9] || [s4 && s10] || [s7 && s11]]] * ([s8_primed==s8])) * (1 * ([s9_primed==s10])) * (1 * ([s10_primed==s11])) * (1 * ([s11_primed==0] * (1) + [s11_primed==1] * (1))))" } }, "goal_state": { "fake_goal": 1 }, "initial_state": { "fake_goal": 0, "s0": 0, "s1": 0, "s10": 0, "s11": 0, "s2": 0, "s3": 0, "s4": 0, "s5": 0, "s6": 1, "s7": 0, "s8": 0, "s9": 0 }, "variables": { "fake_goal": { "domain": 2 }, "s0": { "domain": 2 }, "s1": { "domain": 2 }, "s10": { "domain": 2 }, "s11": { "domain": 2 }, "s2": { "domain": 2 }, "s3": { "domain": 2 }, "s4": { "domain": 2 }, "s5": { "domain": 2 }, "s6": { "domain": 2 }, "s7": { "domain": 2 }, "s8": { "domain": 2 }, "s9": { "domain": 2 } } } Original ordering: s0 s1 s2 s3 s4 s5 s6 s7 s8 s9 s10 s11 fake_goal Build ast.....done! Compute fan-in...done! Fan-in ordering: fake_goal s11 s10 s9 s7 s6 s5 s4 s3 s2 s1 s0 s8 [s0 : 11] [s1 : 10] [s2 : 9] [s3 : 8] [s4 : 7] [s5 : 6] [s6 : 5] [s7 : 4] [s8 : 12] [s9 : 3] [s10 : 2] [s11 : 1] [fake_goal : 0] Num variables: 13 => 13 [ incl. primed: 26 ] move(x1, y1) ......overall time: 0.14 => Time left: 24.86s move(x1, y2) ......overall time: 0.27 => Time left: 24.73s move(x1, y3) ......overall time: 0.39 => Time left: 24.61s move(x2, y1) ......overall time: 0.52 => Time left: 24.48s move(x2, y2) ......overall time: 0.65 => Time left: 24.35s move(x2, y3) ......overall time: 0.78 => Time left: 24.22s move(x3, y1) ......overall time: 0.9 => Time left: 24.1s move(x3, y2) ......overall time: 1.03 => Time left: 23.97s move(x3, y3) ......overall time: 1.15 => Time left: 23.85s noop......overall time: 1.28 => Time left: 23.72s Plan step 1/50... ...worst value: 1 ...overall worst value: 1 ...overall time: 1.28 => Time left: 23.72s Plan step 2/50... ...worst value: 2 ...overall worst value: 2 ...overall time: 1.28 => Time left: 23.72s Plan step 3/50... ...worst value: 3 ...overall worst value: 3 ...overall time: 1.28 => Time left: 23.72s Plan step 4/50... ...worst value: 4 ...overall worst value: 4 ...overall time: 1.28 => Time left: 23.72s Plan step 5/50... ...worst value: 5 ...overall worst value: 5 ...overall time: 1.28 => Time left: 23.72s Plan step 6/50... ...worst value: 6 ...overall worst value: 6 ...overall time: 1.28 => Time left: 23.72s Plan step 7/50... ...worst value: 7 ...overall worst value: 7 ...overall time: 1.28 => Time left: 23.72s Plan step 8/50... ...worst value: 8 ...overall worst value: 8 ...overall time: 1.28 => Time left: 23.72s Plan step 9/50... ...worst value: 9 ...overall worst value: 9 ...overall time: 1.28 => Time left: 23.72s Plan step 10/50... ...worst value: 10 ...overall worst value: 10 ...overall time: 1.28 => Time left: 23.72s Plan step 11/50... ...worst value: 11 ...overall worst value: 11 ...overall time: 1.29 => Time left: 23.71s Plan step 12/50... ...worst value: 12 ...overall worst value: 12 ...overall time: 1.29 => Time left: 23.71s Plan step 13/50... ...worst value: 13 ...overall worst value: 13 ...overall time: 1.29 => Time left: 23.71s Plan step 14/50... ...worst value: 14 ...overall worst value: 14 ...overall time: 1.29 => Time left: 23.71s Plan step 15/50... ...worst value: 15 ...overall worst value: 15 ...overall time: 1.29 => Time left: 23.71s Plan step 16/50... ...worst value: 16 ...overall worst value: 16 ...overall time: 1.29 => Time left: 23.71s Plan step 17/50... ...worst value: 17 ...overall worst value: 17 ...overall time: 1.29 => Time left: 23.71s Plan step 18/50... ...worst value: 18 ...overall worst value: 18 ...overall time: 1.29 => Time left: 23.71s Plan step 19/50... ...worst value: 19 ...overall worst value: 19 ...overall time: 1.29 => Time left: 23.71s Plan step 20/50... ...worst value: 20 ...overall worst value: 20 ...overall time: 1.29 => Time left: 23.71s Plan step 21/50... ...worst value: 21 ...overall worst value: 21 ...overall time: 1.29 => Time left: 23.71s Plan step 22/50... ...worst value: 22 ...overall worst value: 22 ...overall time: 1.29 => Time left: 23.71s Plan step 23/50... ...worst value: 23 ...overall worst value: 23 ...overall time: 1.29 => Time left: 23.71s Plan step 24/50... ...worst value: 24 ...overall worst value: 24 ...overall time: 1.29 => Time left: 23.71s Plan step 25/50... ...worst value: 25 ...overall worst value: 25 ...overall time: 1.29 => Time left: 23.71s Plan step 26/50... ...worst value: 26 ...overall worst value: 26 ...overall time: 1.29 => Time left: 23.71s Plan step 27/50... ...worst value: 27 ...overall worst value: 27 ...overall time: 1.29 => Time left: 23.71s Plan step 28/50... ...worst value: 28 ...overall worst value: 28 ...overall time: 1.3 => Time left: 23.7s Plan step 29/50... ...worst value: 29 ...overall worst value: 29 ...overall time: 1.3 => Time left: 23.7s Plan step 30/50... ...worst value: 30 ...overall worst value: 30 ...overall time: 1.31 => Time left: 23.69s Plan step 31/50... ...worst value: 31 ...overall worst value: 31 ...overall time: 1.31 => Time left: 23.69s Plan step 32/50... ...worst value: 32 ...overall worst value: 32 ...overall time: 1.31 => Time left: 23.69s Plan step 33/50... ...worst value: 33 ...overall worst value: 33 ...overall time: 1.31 => Time left: 23.69s Plan step 34/50... ...worst value: 34 ...overall worst value: 34 ...overall time: 1.31 => Time left: 23.69s Plan step 35/50... ...worst value: 35 ...overall worst value: 35 ...overall time: 1.31 => Time left: 23.69s Plan step 36/50... ...worst value: 36 ...overall worst value: 36 ...overall time: 1.31 => Time left: 23.69s Plan step 37/50... ...worst value: 37 ...overall worst value: 37 ...overall time: 1.31 => Time left: 23.69s Plan step 38/50... ...worst value: 38 ...overall worst value: 38 ...overall time: 1.31 => Time left: 23.69s Plan step 39/50... ...worst value: 39 ...overall worst value: 39 ...overall time: 1.31 => Time left: 23.69s Plan step 40/50... ...worst value: 40 ...overall worst value: 40 ...overall time: 1.31 => Time left: 23.69s Plan step 41/50... ...worst value: 41 ...overall worst value: 41 ...overall time: 1.31 => Time left: 23.69s Plan step 42/50... ...worst value: 42 ...overall worst value: 42 ...overall time: 1.31 => Time left: 23.69s Plan step 43/50... ...worst value: 43 ...overall worst value: 43 ...overall time: 1.32 => Time left: 23.68s Plan step 44/50... ...worst value: 44 ...overall worst value: 44 ...overall time: 1.32 => Time left: 23.68s Plan step 45/50... ...worst value: 45 ...overall worst value: 45 ...overall time: 1.32 => Time left: 23.68s Plan step 46/50... ...worst value: 46 ...overall worst value: 46 ...overall time: 1.32 => Time left: 23.68s Plan step 47/50... ...worst value: 47 ...overall worst value: 47 ...overall time: 1.32 => Time left: 23.68s Plan step 48/50... ...worst value: 48 ...overall worst value: 48 ...overall time: 1.32 => Time left: 23.68s Plan step 49/50... ...worst value: 49 ...overall worst value: 49 ...overall time: 1.32 => Time left: 23.68s Plan step 50/50... ...worst value: 50 ...overall worst value: 50 ...overall time: 1.32 => Time left: 23.68s Completed layers: 51 Reset Det Task. ... finished THTS: ...finished ...finished (1.39297s). Final task: ----------------Actions--------------- Action fluents: move(x1, y1) move(x1, y2) move(x1, y3) move(x2, y1) move(x2, y2) move(x2, y3) move(x3, y1) move(x3, y2) move(x3, y3) --------------- Legal Action Combinations: noop() : Index : 0 Relevant preconditions: --------------- move(x3, y3) : Index : 1 Relevant preconditions: Precond 8 Precond 17 --------------- move(x3, y2) : Index : 2 Relevant preconditions: Precond 7 Precond 16 --------------- move(x3, y1) : Index : 3 Relevant preconditions: Precond 6 Precond 15 --------------- move(x2, y3) : Index : 4 Relevant preconditions: Precond 5 Precond 14 --------------- move(x2, y2) : Index : 5 Relevant preconditions: Precond 4 Precond 13 --------------- move(x2, y1) : Index : 6 Relevant preconditions: Precond 3 Precond 12 --------------- move(x1, y3) : Index : 7 Relevant preconditions: Precond 2 Precond 11 --------------- move(x1, y2) : Index : 8 Relevant preconditions: Precond 1 Precond 10 --------------- move(x1, y1) : Index : 9 Relevant preconditions: Precond 0 Precond 9 --------------- -----------------CPFs----------------- agent-at(x1, y1) HashIndex: 0, deterministic, caching in vectors, Kleene caching in vectors of size 21870. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x1, y1) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x1, y1)) Domain: false true HashKeyBase: 0: 0, 1: 1 KleeneHashKeyBase: 1 -------------- agent-at(x1, y2) HashIndex: 1, deterministic, caching in vectors, Kleene caching in vectors of size 7290. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x1, y2) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x1, y2)) Domain: false true HashKeyBase: 0: 0, 1: 2 KleeneHashKeyBase: 3 -------------- agent-at(x1, y3) HashIndex: 2, deterministic, caching in vectors, Kleene caching in vectors of size 21870. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x1, y3) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x1, y3)) Domain: false true HashKeyBase: 0: 0, 1: 4 KleeneHashKeyBase: 9 -------------- agent-at(x2, y1) HashIndex: 3, deterministic, caching in vectors, Kleene caching in vectors of size 21870. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x2, y1) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x2, y1)) Domain: false true HashKeyBase: 0: 0, 1: 8 KleeneHashKeyBase: 27 -------------- agent-at(x2, y2) HashIndex: 4, deterministic, caching in vectors, Kleene caching in vectors of size 7290. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x2, y2) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x2, y2)) Domain: false true HashKeyBase: 0: 0, 1: 16 KleeneHashKeyBase: 81 -------------- agent-at(x2, y3) HashIndex: 5, deterministic, caching in vectors, Kleene caching in vectors of size 21870. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x2, y3) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x2, y3)) Domain: false true HashKeyBase: 0: 0, 1: 32 KleeneHashKeyBase: 243 -------------- agent-at(x3, y1) HashIndex: 6, deterministic, caching in vectors, Kleene caching in vectors of size 21870. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x3, y1) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x3, y1)) Domain: false true HashKeyBase: 0: 0, 1: 64 KleeneHashKeyBase: 729 -------------- agent-at(x3, y2) HashIndex: 7, deterministic, caching in vectors, Kleene caching in vectors of size 7290. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x3, y2) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x3, y2)) Domain: false true HashKeyBase: 0: 0, 1: 128 KleeneHashKeyBase: 2187 -------------- agent-at(x3, y3) HashIndex: 8, deterministic, caching in vectors, Kleene caching in vectors of size 21870. Action Hash Key Map: move(x3, y3) : 1 move(x3, y2) : 2 move(x3, y1) : 3 move(x2, y3) : 4 move(x2, y2) : 5 move(x2, y1) : 6 move(x1, y3) : 7 move(x1, y2) : 8 move(x1, y1) : 9 Formula: case (or (and agent-at(x1, y2) obstacle-at(x1, y2)) (and agent-at(x2, y2) obstacle-at(x2, y2)) (and agent-at(x3, y2) obstacle-at(x3, y2)) ) then 0 case move(x3, y3) then 1 case 1 then (and (not move(x1, y1)) (not move(x1, y2)) (not move(x1, y3)) (not move(x2, y1)) (not move(x2, y2)) (not move(x2, y3)) (not move(x3, y1)) (not move(x3, y2)) (not move(x3, y3)) agent-at(x3, y3)) Domain: false true HashKeyBase: 0: 0, 1: 256 KleeneHashKeyBase: 6561 -------------- obstacle-at(x1, y2) HashIndex: 9, deterministic, caching in vectors, Kleene caching in vectors of size 3. Action Hash Key Map: Formula: obstacle-at(x2, y2) Domain: false true HashKeyBase: 0: 0, 1: 512 KleeneHashKeyBase: 19683 -------------- obstacle-at(x2, y2) HashIndex: 10, deterministic, caching in vectors, Kleene caching in vectors of size 3. Action Hash Key Map: Formula: obstacle-at(x3, y2) Domain: false true HashKeyBase: 0: 0, 1: 1024 KleeneHashKeyBase: 59049 -------------- obstacle-at(x3, y2) HashIndex: 11, probabilistic, caching in vectors, Kleene caching in vectors of size 1. Action Hash Key Map: Formula: Bernoulli(0.3) Determinized formula: 0 Domain: false true HashKeyBase: 0: 0, 1: 2048 KleeneHashKeyBase: 177147 -------------- Reward CPF: Reward HashIndex: 12, deterministic, caching in vectors, Kleene caching in vectors of size 3. Action Hash Key Map: Formula: (- 0 (not agent-at(x3, y3)) ) Minimal reward: -1 Maximal reward: 0 Is action independent: 1 ------State Fluent Hash Key Map------- a change of deterministic state fluent 0 influences variables 0 (10) 14 (2) 16 (2) a change of deterministic state fluent 1 influences variables 0 (20) 1 (10) 2 (10) 3 (10) 4 (10) 5 (10) 6 (10) 7 (10) 8 (10) 13 (2) 15 (2) 17 (2) a change of deterministic state fluent 2 influences variables 2 (20) 14 (4) 18 (2) a change of deterministic state fluent 3 influences variables 3 (20) 13 (4) 17 (4) 19 (2) a change of deterministic state fluent 4 influences variables 0 (40) 1 (20) 2 (40) 3 (40) 4 (20) 5 (20) 6 (20) 7 (20) 8 (20) 14 (8) 16 (4) 18 (4) 20 (2) a change of deterministic state fluent 5 influences variables 5 (40) 15 (4) 17 (8) 21 (2) a change of deterministic state fluent 6 influences variables 6 (40) 16 (8) 20 (4) a change of deterministic state fluent 7 influences variables 0 (80) 1 (40) 2 (80) 3 (80) 4 (40) 5 (80) 6 (80) 7 (40) 8 (40) 17 (16) 19 (4) 21 (4) a change of deterministic state fluent 8 influences variables 8 (80) 12 (1) 18 (8) 20 (8) 22 (2) 23 (2) 24 (2) 25 (2) 26 (2) 27 (2) 28 (2) 29 (2) 30 (2) a change of deterministic state fluent 9 influences variables 0 (160) 1 (80) 2 (160) 3 (160) 4 (80) 5 (160) 6 (160) 7 (80) 8 (160) a change of deterministic state fluent 10 influences variables 0 (320) 1 (160) 2 (320) 3 (320) 4 (160) 5 (320) 6 (320) 7 (160) 8 (320) 9 (1) a change of probabilistic state fluent 0 influences variables 0 (640) 1 (320) 2 (640) 3 (640) 4 (320) 5 (640) 6 (640) 7 (320) 8 (640) 10 (1) a change of variable 0 influences variables in Kleene states 0 (10) 14 (2) 16 (2) a change of variable 1 influences variables in Kleene states 0 (30) 1 (10) 2 (10) 3 (10) 4 (10) 5 (10) 6 (10) 7 (10) 8 (10) 13 (2) 15 (2) 17 (2) a change of variable 2 influences variables in Kleene states 2 (30) 14 (6) 18 (2) a change of variable 3 influences variables in Kleene states 3 (30) 13 (6) 17 (6) 19 (2) a change of variable 4 influences variables in Kleene states 0 (90) 1 (30) 2 (90) 3 (90) 4 (30) 5 (30) 6 (30) 7 (30) 8 (30) 14 (18) 16 (6) 18 (6) 20 (2) a change of variable 5 influences variables in Kleene states 5 (90) 15 (6) 17 (18) 21 (2) a change of variable 6 influences variables in Kleene states 6 (90) 16 (18) 20 (6) a change of variable 7 influences variables in Kleene states 0 (270) 1 (90) 2 (270) 3 (270) 4 (90) 5 (270) 6 (270) 7 (90) 8 (90) 17 (54) 19 (6) 21 (6) a change of variable 8 influences variables in Kleene states 8 (270) 12 (1) 18 (18) 20 (18) 22 (2) 23 (2) 24 (2) 25 (2) 26 (2) 27 (2) 28 (2) 29 (2) 30 (2) a change of variable 9 influences variables in Kleene states 0 (810) 1 (270) 2 (810) 3 (810) 4 (270) 5 (810) 6 (810) 7 (270) 8 (810) a change of variable 10 influences variables in Kleene states 0 (2430) 1 (810) 2 (2430) 3 (2430) 4 (810) 5 (2430) 6 (2430) 7 (810) 8 (2430) 9 (1) a change of variable 11 influences variables in Kleene states 0 (7290) 1 (2430) 2 (7290) 3 (7290) 4 (2430) 5 (7290) 6 (7290) 7 (2430) 8 (7290) 10 (1) ---------Action Preconditions--------- Precond 0 HashIndex: 13, deterministic, caching in vectors, Kleene caching in vectors of size 18. Action Hash Key Map: move(x1, y1) : 1 Formula: (or (not move(x1, y1)) agent-at(x1, y2) agent-at(x2, y1)) -------------- Precond 1 HashIndex: 14, deterministic, caching in vectors, Kleene caching in vectors of size 54. Action Hash Key Map: move(x1, y2) : 1 Formula: (or (not move(x1, y2)) agent-at(x1, y1) agent-at(x1, y3) agent-at(x2, y2)) -------------- Precond 2 HashIndex: 15, deterministic, caching in vectors, Kleene caching in vectors of size 18. Action Hash Key Map: move(x1, y3) : 1 Formula: (or (not move(x1, y3)) agent-at(x1, y2) agent-at(x2, y3)) -------------- Precond 3 HashIndex: 16, deterministic, caching in vectors, Kleene caching in vectors of size 54. Action Hash Key Map: move(x2, y1) : 1 Formula: (or (not move(x2, y1)) agent-at(x1, y1) agent-at(x2, y2) agent-at(x3, y1)) -------------- Precond 4 HashIndex: 17, deterministic, caching in vectors, Kleene caching in vectors of size 162. Action Hash Key Map: move(x2, y2) : 1 Formula: (or (not move(x2, y2)) agent-at(x1, y2) agent-at(x2, y1) agent-at(x2, y3) agent-at(x3, y2)) -------------- Precond 5 HashIndex: 18, deterministic, caching in vectors, Kleene caching in vectors of size 54. Action Hash Key Map: move(x2, y3) : 1 Formula: (or (not move(x2, y3)) agent-at(x1, y3) agent-at(x2, y2) agent-at(x3, y3)) -------------- Precond 6 HashIndex: 19, deterministic, caching in vectors, Kleene caching in vectors of size 18. Action Hash Key Map: move(x3, y1) : 1 Formula: (or (not move(x3, y1)) agent-at(x2, y1) agent-at(x3, y2)) -------------- Precond 7 HashIndex: 20, deterministic, caching in vectors, Kleene caching in vectors of size 54. Action Hash Key Map: move(x3, y2) : 1 Formula: (or (not move(x3, y2)) agent-at(x2, y2) agent-at(x3, y1) agent-at(x3, y3)) -------------- Precond 8 HashIndex: 21, deterministic, caching in vectors, Kleene caching in vectors of size 18. Action Hash Key Map: move(x3, y3) : 1 Formula: (or (not move(x3, y3)) agent-at(x2, y3) agent-at(x3, y2)) -------------- Precond 9 HashIndex: 22, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x1, y1) : 1 Formula: (or (not move(x1, y1)) (not agent-at(x3, y3)) ) -------------- Precond 10 HashIndex: 23, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x1, y2) : 1 Formula: (or (not move(x1, y2)) (not agent-at(x3, y3)) ) -------------- Precond 11 HashIndex: 24, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x1, y3) : 1 Formula: (or (not move(x1, y3)) (not agent-at(x3, y3)) ) -------------- Precond 12 HashIndex: 25, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x2, y1) : 1 Formula: (or (not move(x2, y1)) (not agent-at(x3, y3)) ) -------------- Precond 13 HashIndex: 26, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x2, y2) : 1 Formula: (or (not move(x2, y2)) (not agent-at(x3, y3)) ) -------------- Precond 14 HashIndex: 27, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x2, y3) : 1 Formula: (or (not move(x2, y3)) (not agent-at(x3, y3)) ) -------------- Precond 15 HashIndex: 28, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x3, y1) : 1 Formula: (or (not move(x3, y1)) (not agent-at(x3, y3)) ) -------------- Precond 16 HashIndex: 29, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x3, y2) : 1 Formula: (or (not move(x3, y2)) (not agent-at(x3, y3)) ) -------------- Precond 17 HashIndex: 30, deterministic, caching in vectors, Kleene caching in vectors of size 6. Action Hash Key Map: move(x3, y3) : 1 Formula: (or (not move(x3, y3)) (not agent-at(x3, y3)) ) -------------- ----------Initial State--------------- agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 1 agent-at(x3, y2): 0 agent-at(x3, y3): 0 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 50 StateHashKey: 64 Hashing of States is possible. Hashing of KleeneStates is possible. Both a goal and a dead end were found in the training phase. This task contains unreasonable actions. The final reward is determined by applying NOOP. *********************************************** >>> STARTING ROUND 1 -- REMAINING TIME 198s *********************************************** *********************************************** Planning step 1/50 in round 1/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.39097s. THTS: Maximal search depth set to 50 Search time: 0.390974s Statistics of THTS: Performed trials: 21568 Created SearchNodes: 68742 Cache Hits: 8387 Action Selection: Exploitation in Root: 20753 Exploration in Root: 815 Percentage Exploration in Root: 0.0377875 Skipped backups: 386106 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42583 (in 21571 real visits) Q-Value Estimates: noop() : -5.336 (in 415 real visits) move(x3, y2) : -16.4 (in 415 real visits) move(x2, y1) : -4.42583 (in 20741 real visits) Used RAM: 334916 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 1/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 0.390966s. THTS: Maximal search depth set to 49 Search time: 0.390978s Statistics of THTS: Performed trials: 22639 Created SearchNodes: 70903 Cache Hits: 9486 Skipped backups: 798488 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 22643 real visits) Q-Value Estimates: noop() : -4.363 (in 428 real visits) move(x3, y1) : -5.3 (in 428 real visits) move(x2, y2) : -3 (in 21359 real visits) move(x1, y1) : -5 (in 428 real visits) Used RAM: 335176 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 1/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 1 Setting time for this decision to 0.390962s. THTS: Maximal search depth set to 48 Search time: 0.390983s Statistics of THTS: Performed trials: 20699 Created SearchNodes: 63742 Cache Hits: 8701 Skipped backups: 1178760 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 20704 real visits) Q-Value Estimates: noop() : -48 (in 384 real visits) move(x3, y2) : -15.8 (in 384 real visits) move(x2, y3) : -2 (in 19168 real visits) move(x2, y1) : -4.39 (in 384 real visits) move(x1, y2) : -4 (in 384 real visits) Used RAM: 335176 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 1/10 Current state: 0 0 0 0 0 1 0 0 0 0 1 | 1 Setting time for this decision to 0.390958s. THTS: Maximal search depth set to 47 Search time: 0.390976s Statistics of THTS: Performed trials: 22816 Created SearchNodes: 70158 Cache Hits: 9684 Skipped backups: 1615946 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 22820 real visits) Q-Value Estimates: noop() : -2 (in 21939 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -47 (in 439 real visits) move(x1, y3) : -3 (in 439 real visits) Used RAM: 335176 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.390952s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 46 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.391733s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.39252s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.393312s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.394106s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 42 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.394904s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 41 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.395704s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.396509s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.397318s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.398127s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.398942s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 36 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.399759s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.400581s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.401406s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.402232s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.403062s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 31 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.403896s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.404733s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 29 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.405575s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 28 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.406419s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.407269s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 26 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.40812s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.408977s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.409837s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 23 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.410699s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.411567s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 21 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.412436s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.413311s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 19 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.414188s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 18 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.415071s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 17 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.415957s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 16 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.416845s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.417737s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 14 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.418635s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.419537s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 12 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.42044s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 11 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.42135s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.422261s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 9 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.423179s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 8 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.424101s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 7 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.425024s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.425954s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.426885s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 4 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.427823s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.428765s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 1/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.42971s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 21568 Accumulated number of search nodes in root state: 68742 Used RAM: 335176 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 1 -- REWARD RECEIVED: -4 *********************************************** *********************************************** >>> STARTING ROUND 2 -- REMAINING TIME 196s *********************************************** *********************************************** Planning step 1/50 in round 2/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.430658s. THTS: Maximal search depth set to 50 Search time: 0.430669s Statistics of THTS: Performed trials: 24214 Created SearchNodes: 77200 Cache Hits: 9551 Action Selection: Exploitation in Root: 23292 Exploration in Root: 922 Percentage Exploration in Root: 0.0380771 Skipped backups: 2056710 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.4251 (in 24217 real visits) Q-Value Estimates: noop() : -5.3171 (in 466 real visits) move(x3, y2) : -16.4 (in 466 real visits) move(x2, y1) : -4.4251 (in 23285 real visits) Used RAM: 335924 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 2/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 0.430655s. THTS: Maximal search depth set to 49 Search time: 0.430659s Statistics of THTS: Performed trials: 24193 Created SearchNodes: 75924 Cache Hits: 10089 Skipped backups: 2500434 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 24197 real visits) Q-Value Estimates: noop() : -4.363 (in 457 real visits) move(x3, y1) : -5.39 (in 457 real visits) move(x2, y2) : -3 (in 22826 real visits) move(x1, y1) : -5 (in 457 real visits) Used RAM: 335924 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 2/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 1 Setting time for this decision to 0.43065s. THTS: Maximal search depth set to 48 Search time: 0.430661s Statistics of THTS: Performed trials: 25326 Created SearchNodes: 77780 Cache Hits: 10695 Skipped backups: 2979496 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 25331 real visits) Q-Value Estimates: noop() : -48 (in 470 real visits) move(x3, y2) : -15.8 (in 470 real visits) move(x2, y3) : -2 (in 23451 real visits) move(x2, y1) : -4.39 (in 470 real visits) move(x1, y2) : -4 (in 470 real visits) Used RAM: 335924 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 2/10 Current state: 0 0 0 0 0 1 0 0 0 0 1 | 1 Setting time for this decision to 0.430647s. THTS: Maximal search depth set to 47 Search time: 0.430652s Statistics of THTS: Performed trials: 25338 Created SearchNodes: 77830 Cache Hits: 10791 Skipped backups: 3470230 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 25342 real visits) Q-Value Estimates: noop() : -2 (in 24363 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -47 (in 488 real visits) move(x1, y3) : -3 (in 488 real visits) Used RAM: 335924 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.430641s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 46 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.4316s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.432565s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.433537s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.434511s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 42 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.435492s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 41 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.436475s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.437465s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 39 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.438457s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.439455s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.440456s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 36 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.441464s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.442475s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.44349s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 33 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.444512s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 32 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.445536s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.446567s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.447601s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 29 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.448643s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 28 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.449686s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.450737s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.451791s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 25 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.452851s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 24 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.453915s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 23 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.454986s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 22 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.456059s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 21 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.45714s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.458224s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 19 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.459316s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 18 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.46041s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.461512s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.462617s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.463729s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 14 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.464845s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.465968s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 12 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.467095s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 11 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.468227s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 10 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.469367s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 9 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.47051s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 8 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.471661s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.472815s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.473978s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.475141s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 4 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.476315s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 3 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.477493s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 2/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.478676s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 45782 Accumulated number of search nodes in root state: 145942 Used RAM: 335924 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 2 -- REWARD RECEIVED: -4 *********************************************** *********************************************** >>> STARTING ROUND 3 -- REMAINING TIME 194s *********************************************** *********************************************** Planning step 1/50 in round 3/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.479868s. THTS: Maximal search depth set to 50 Search time: 0.479884s Statistics of THTS: Performed trials: 27024 Created SearchNodes: 85961 Cache Hits: 10715 Action Selection: Exploitation in Root: 25997 Exploration in Root: 1027 Percentage Exploration in Root: 0.0380033 Skipped backups: 3969708 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.4268 (in 27027 real visits) Q-Value Estimates: noop() : -5.3189 (in 520 real visits) move(x3, y2) : -16.4 (in 520 real visits) move(x2, y1) : -4.4268 (in 25987 real visits) Used RAM: 336712 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 3/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 0.479862s. THTS: Maximal search depth set to 49 Search time: 0.479867s Statistics of THTS: Performed trials: 27597 Created SearchNodes: 86478 Cache Hits: 11540 Skipped backups: 4486636 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 27601 real visits) Q-Value Estimates: noop() : -4.39 (in 521 real visits) move(x3, y1) : -5.3189 (in 521 real visits) move(x2, y2) : -3 (in 26038 real visits) move(x1, y1) : -5 (in 521 real visits) Used RAM: 336976 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 3/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 0 Setting time for this decision to 0.479857s. THTS: Maximal search depth set to 48 Search time: 0.479867s Statistics of THTS: Performed trials: 28131 Created SearchNodes: 87230 Cache Hits: 12052 Skipped backups: 5023354 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 28136 real visits) Q-Value Estimates: noop() : -3 (in 522 real visits) move(x3, y2) : -15.8 (in 521 real visits) move(x2, y3) : -2 (in 26051 real visits) move(x2, y1) : -4.363 (in 521 real visits) move(x1, y2) : -4 (in 521 real visits) Used RAM: 336976 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 3/10 Current state: 0 0 0 0 0 1 0 0 0 0 0 | 0 Setting time for this decision to 0.479851s. THTS: Maximal search depth set to 47 Search time: 0.479874s Statistics of THTS: Performed trials: 28046 Created SearchNodes: 86702 Cache Hits: 12195 Skipped backups: 5572530 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 28050 real visits) Q-Value Estimates: noop() : -2 (in 26967 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 540 real visits) move(x1, y3) : -3 (in 540 real visits) Used RAM: 336976 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.479848s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 46 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.481051s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 45 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.482264s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.483486s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 43 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.484712s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 42 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.485946s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 41 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.487185s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 40 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.488432s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.489683s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 38 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.490941s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 37 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.492205s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 36 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.493478s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.494755s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.496042s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.497332s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.498633s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.499937s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.501248s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 29 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.502569s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 28 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.503894s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 27 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.505229s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.506568s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.507917s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.509271s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 23 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.510632s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.512003s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 21 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.513378s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 20 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.514764s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 19 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.516155s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 18 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.517556s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.518962s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.520375s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.521799s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 14 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.523229s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 13 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.524669s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 12 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.526114s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 11 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.527567s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.529028s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 9 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.5305s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 8 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.531978s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 7 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.533463s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.534961s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.536463s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 4 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.537977s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.539497s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 2 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 3/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.541028s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 72806 Accumulated number of search nodes in root state: 231903 Used RAM: 336976 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 3 -- REWARD RECEIVED: -4 *********************************************** *********************************************** >>> STARTING ROUND 4 -- REMAINING TIME 192s *********************************************** *********************************************** Planning step 1/50 in round 4/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.542566s. THTS: Maximal search depth set to 50 Search time: 0.542575s Statistics of THTS: Performed trials: 29893 Created SearchNodes: 94977 Cache Hits: 11879 Action Selection: Exploitation in Root: 28755 Exploration in Root: 1138 Percentage Exploration in Root: 0.0380691 Skipped backups: 6132486 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.4268 (in 29896 real visits) Q-Value Estimates: noop() : -5.39 (in 575 real visits) move(x3, y2) : -16.4 (in 575 real visits) move(x2, y1) : -4.4268 (in 28746 real visits) Used RAM: 337768 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 4/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 1 Setting time for this decision to 0.542559s. THTS: Maximal search depth set to 49 Search time: 0.542581s Statistics of THTS: Performed trials: 29759 Created SearchNodes: 94397 Cache Hits: 11565 Skipped backups: 6685428 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 29763 real visits) Q-Value Estimates: noop() : -4.42753 (in 28077 real visits) move(x3, y1) : -5.3108 (in 562 real visits) move(x2, y2) : -49 (in 562 real visits) move(x1, y1) : -5.3 (in 562 real visits) Used RAM: 337768 Submitted action: noop() Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 4/10 Current state: 0 0 0 1 0 0 0 0 0 0 1 | 0 Setting time for this decision to 0.542555s. THTS: Maximal search depth set to 48 Search time: 0.542581s Statistics of THTS: Performed trials: 31056 Created SearchNodes: 97050 Cache Hits: 13020 Skipped backups: 7276788 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 31060 real visits) Q-Value Estimates: noop() : -4.39 (in 587 real visits) move(x3, y1) : -5.3711 (in 586 real visits) move(x2, y2) : -3 (in 29301 real visits) move(x1, y1) : -5 (in 586 real visits) Used RAM: 338032 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 4/10 Current state: 0 0 0 0 1 0 0 0 0 1 0 | 0 Setting time for this decision to 0.542548s. THTS: Maximal search depth set to 47 Search time: 0.54256s Statistics of THTS: Performed trials: 31401 Created SearchNodes: 97334 Cache Hits: 13440 Skipped backups: 7885018 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 31406 real visits) Q-Value Estimates: noop() : -3 (in 582 real visits) move(x3, y2) : -15.5 (in 582 real visits) move(x2, y3) : -2 (in 29078 real visits) move(x2, y1) : -4.363 (in 582 real visits) move(x1, y2) : -4 (in 582 real visits) Used RAM: 338032 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 4/10 Current state: 0 0 0 0 0 1 0 0 0 0 0 | 0 Setting time for this decision to 0.542543s. THTS: Maximal search depth set to 46 Search time: 0.542554s Statistics of THTS: Performed trials: 31730 Created SearchNodes: 97958 Cache Hits: 13795 Skipped backups: 8515036 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 31734 real visits) Q-Value Estimates: noop() : -2 (in 30509 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 611 real visits) move(x1, y3) : -3 (in 611 real visits) Used RAM: 338032 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 6/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.542539s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.544102s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.545679s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.547269s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 42 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.548865s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 41 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.550471s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.552086s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.553713s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.555347s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.556994s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 36 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.558648s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.560311s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 34 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.561988s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.563672s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.565366s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.56707s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.568787s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 29 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.570512s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 28 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.572251s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.573997s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 26 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.575757s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.577525s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 24 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.579303s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 23 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.581096s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.582897s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 21 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.584709s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.586536s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 19 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.588371s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 18 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.590218s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 17 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.592079s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.593949s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 15 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.595834s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 14 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.597728s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.599635s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 12 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.601553s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 11 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.603484s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 10 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.60543s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 9 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.607386s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 8 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.609355s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.61134s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.613334s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.615342s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 4 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.617366s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.619401s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 4/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.621449s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 102699 Accumulated number of search nodes in root state: 326880 Used RAM: 338032 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 4 -- REWARD RECEIVED: -5 *********************************************** *********************************************** >>> STARTING ROUND 5 -- REMAINING TIME 190s *********************************************** *********************************************** Planning step 1/50 in round 5/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.623507s. THTS: Maximal search depth set to 50 Search time: 0.623528s Statistics of THTS: Performed trials: 34590 Created SearchNodes: 109479 Cache Hits: 13870 Action Selection: Exploitation in Root: 33287 Exploration in Root: 1303 Percentage Exploration in Root: 0.0376698 Skipped backups: 9177922 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.4268 (in 34593 real visits) Q-Value Estimates: noop() : -5.3441 (in 666 real visits) move(x3, y2) : -16.4 (in 666 real visits) move(x2, y1) : -4.4268 (in 33261 real visits) Used RAM: 339344 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 5/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 0.623502s. THTS: Maximal search depth set to 49 Search time: 0.623518s Statistics of THTS: Performed trials: 35337 Created SearchNodes: 110206 Cache Hits: 14830 Skipped backups: 9860664 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 35341 real visits) Q-Value Estimates: noop() : -4.39 (in 667 real visits) move(x3, y1) : -5.3441 (in 667 real visits) move(x2, y2) : -3 (in 33340 real visits) move(x1, y1) : -5 (in 667 real visits) Used RAM: 339344 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 5/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 1 Setting time for this decision to 0.623493s. THTS: Maximal search depth set to 48 Search time: 0.623497s Statistics of THTS: Performed trials: 35489 Created SearchNodes: 108920 Cache Hits: 14965 Skipped backups: 10562002 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 35494 real visits) Q-Value Estimates: noop() : -48 (in 658 real visits) move(x3, y2) : -15.8 (in 658 real visits) move(x2, y3) : -2 (in 32862 real visits) move(x2, y1) : -4.417 (in 658 real visits) move(x1, y2) : -4 (in 658 real visits) Used RAM: 339344 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 5/10 Current state: 0 0 0 0 0 1 0 0 0 0 1 | 0 Setting time for this decision to 0.623488s. THTS: Maximal search depth set to 47 Search time: 0.623516s Statistics of THTS: Performed trials: 36018 Created SearchNodes: 111415 Cache Hits: 15603 Skipped backups: 11289848 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 36022 real visits) Q-Value Estimates: noop() : -2 (in 34633 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 693 real visits) move(x1, y3) : -3 (in 693 real visits) Used RAM: 339344 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.62348s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 46 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.625576s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.627697s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.629829s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.631976s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 42 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.634137s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 41 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.636314s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.638509s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.640715s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.642937s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 37 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.645175s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 36 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.647432s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.649701s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 34 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.651986s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 33 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.654287s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 32 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.656609s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.658943s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.661294s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 29 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.663662s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 28 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.666051s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.668453s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.670873s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.67331s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.675769s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 23 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.678243s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.680734s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 21 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.683244s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.685777s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 19 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.688325s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 18 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.690891s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.693477s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 16 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.696087s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.698712s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 14 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.701357s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.704023s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 12 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.706709s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 11 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.709415s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.712143s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 9 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.714895s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 8 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.717665s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.720457s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.723271s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.72611s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 4 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.728968s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.731849s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 5/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.734757s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 137289 Accumulated number of search nodes in root state: 436359 Used RAM: 339344 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 5 -- REWARD RECEIVED: -4 *********************************************** *********************************************** >>> STARTING ROUND 6 -- REMAINING TIME 187s *********************************************** *********************************************** Planning step 1/50 in round 6/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.73768s. THTS: Maximal search depth set to 50 Search time: 0.737698s Statistics of THTS: Performed trials: 40474 Created SearchNodes: 127700 Cache Hits: 16278 Action Selection: Exploitation in Root: 38926 Exploration in Root: 1548 Percentage Exploration in Root: 0.0382468 Skipped backups: 12079358 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 40477 real visits) Q-Value Estimates: noop() : -5.3819 (in 779 real visits) move(x3, y2) : -16.4 (in 779 real visits) move(x2, y1) : -4.42753 (in 38919 real visits) Used RAM: 341304 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 6/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 0.737675s. THTS: Maximal search depth set to 49 Search time: 0.737698s Statistics of THTS: Performed trials: 41583 Created SearchNodes: 129481 Cache Hits: 17520 Skipped backups: 12901174 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 41587 real visits) Q-Value Estimates: noop() : -4.4071 (in 785 real visits) move(x3, y1) : -5.3522 (in 785 real visits) move(x2, y2) : -3 (in 39232 real visits) move(x1, y1) : -5 (in 785 real visits) Used RAM: 341304 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 6/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 0 Setting time for this decision to 0.737665s. THTS: Maximal search depth set to 48 Search time: 0.737681s Statistics of THTS: Performed trials: 41954 Created SearchNodes: 129785 Cache Hits: 17953 Skipped backups: 13744116 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 41959 real visits) Q-Value Estimates: noop() : -3 (in 777 real visits) move(x3, y2) : -15.8 (in 777 real visits) move(x2, y3) : -2 (in 38851 real visits) move(x2, y1) : -4.39 (in 777 real visits) move(x1, y2) : -4 (in 777 real visits) Used RAM: 341304 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 6/10 Current state: 0 0 0 0 0 1 0 0 0 0 0 | 0 Setting time for this decision to 0.73766s. THTS: Maximal search depth set to 47 Search time: 0.737689s Statistics of THTS: Performed trials: 42157 Created SearchNodes: 130235 Cache Hits: 18277 Skipped backups: 14611848 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 42161 real visits) Q-Value Estimates: noop() : -2 (in 40536 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 811 real visits) move(x1, y3) : -3 (in 811 real visits) Used RAM: 341568 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.73765s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 46 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.740637s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.74366s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.746704s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.749781s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 42 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.75288s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 41 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.756004s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.759155s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.762336s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.76554s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.768771s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 36 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.77203s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.775316s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 34 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.778631s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.781978s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.785351s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 31 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.788752s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 30 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 0.792183s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 29 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.795645s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 28 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.799137s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.802659s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 26 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.806213s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.809799s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.813417s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 23 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.817068s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 22 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.820756s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 21 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.824473s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.828224s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 19 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.832009s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 18 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.835829s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.839685s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 16 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.843577s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.847505s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 14 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.851474s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.855476s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 12 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.859517s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 11 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.863595s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.867713s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 9 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.87187s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 8 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.876068s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.880306s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.884585s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.888907s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 4 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.893276s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.897683s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 6/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.902134s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 177763 Accumulated number of search nodes in root state: 564059 Used RAM: 341568 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 6 -- REWARD RECEIVED: -4 *********************************************** *********************************************** >>> STARTING ROUND 7 -- REMAINING TIME 184s *********************************************** *********************************************** Planning step 1/50 in round 7/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 0.90663s. THTS: Maximal search depth set to 50 Search time: 0.906639s Statistics of THTS: Performed trials: 49304 Created SearchNodes: 155490 Cache Hits: 19834 Action Selection: Exploitation in Root: 47418 Exploration in Root: 1886 Percentage Exploration in Root: 0.0382525 Skipped backups: 15599838 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42826 (in 49307 real visits) Q-Value Estimates: noop() : -5.3441 (in 949 real visits) move(x3, y2) : -16.4 (in 949 real visits) move(x2, y1) : -4.42826 (in 47409 real visits) Used RAM: 344208 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 7/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 1 Setting time for this decision to 0.906618s. THTS: Maximal search depth set to 49 Search time: 0.906648s Statistics of THTS: Performed trials: 48565 Created SearchNodes: 152883 Cache Hits: 19141 Skipped backups: 16562174 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 48569 real visits) Q-Value Estimates: noop() : -4.42753 (in 45818 real visits) move(x3, y1) : -5.39 (in 917 real visits) move(x2, y2) : -49 (in 917 real visits) move(x1, y1) : -5.3819 (in 917 real visits) Used RAM: 344208 Submitted action: noop() Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 7/10 Current state: 0 0 0 1 0 0 0 0 0 0 1 | 1 Setting time for this decision to 0.906606s. THTS: Maximal search depth set to 48 Search time: 0.906609s Statistics of THTS: Performed trials: 48600 Created SearchNodes: 153067 Cache Hits: 19078 Skipped backups: 17525366 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 48604 real visits) Q-Value Estimates: noop() : -4.42753 (in 45851 real visits) move(x3, y1) : -5.3441 (in 917 real visits) move(x2, y2) : -48 (in 918 real visits) move(x1, y1) : -5.3819 (in 918 real visits) Used RAM: 344208 Submitted action: noop() Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 7/10 Current state: 0 0 0 1 0 0 0 0 0 1 1 | 1 Setting time for this decision to 0.906599s. THTS: Maximal search depth set to 47 Search time: 0.906608s Statistics of THTS: Performed trials: 47571 Created SearchNodes: 149613 Cache Hits: 18741 Skipped backups: 18466786 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 47575 real visits) Q-Value Estimates: noop() : -4.42753 (in 44881 real visits) move(x3, y1) : -5.38433 (in 898 real visits) move(x2, y2) : -47 (in 898 real visits) move(x1, y1) : -5.3801 (in 898 real visits) Used RAM: 344208 Submitted action: noop() Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 7/10 Current state: 0 0 0 1 0 0 0 0 0 1 1 | 0 Setting time for this decision to 0.906587s. THTS: Maximal search depth set to 46 Search time: 0.906597s Statistics of THTS: Performed trials: 48967 Created SearchNodes: 152824 Cache Hits: 20537 Skipped backups: 19454174 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 48971 real visits) Q-Value Estimates: noop() : -4.417 (in 924 real visits) move(x3, y1) : -5.3819 (in 924 real visits) move(x2, y2) : -3 (in 46199 real visits) move(x1, y1) : -5 (in 924 real visits) Used RAM: 344208 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 6/50 in round 7/10 Current state: 0 0 0 0 1 0 0 0 0 1 0 | 0 Setting time for this decision to 0.906579s. THTS: Maximal search depth set to 45 Search time: 0.906591s Statistics of THTS: Performed trials: 50955 Created SearchNodes: 157535 Cache Hits: 21753 Skipped backups: 20503552 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 50960 real visits) Q-Value Estimates: noop() : -3 (in 944 real visits) move(x3, y2) : -14.9 (in 944 real visits) move(x2, y3) : -2 (in 47184 real visits) move(x2, y1) : -4.39 (in 944 real visits) move(x1, y2) : -4 (in 944 real visits) Used RAM: 344208 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 7/50 in round 7/10 Current state: 0 0 0 0 0 1 0 0 0 0 0 | 1 Setting time for this decision to 0.906567s. THTS: Maximal search depth set to 44 Search time: 0.906582s Statistics of THTS: Performed trials: 50456 Created SearchNodes: 154591 Cache Hits: 21377 Skipped backups: 21570226 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 50460 real visits) Q-Value Estimates: noop() : -2 (in 48515 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -44 (in 971 real visits) move(x1, y3) : -3 (in 971 real visits) Used RAM: 344208 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 8/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 0.90656s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 43 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 0.911245s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 42 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.916s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 41 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.920805s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.925661s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.930569s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 38 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.935524s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.940538s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 36 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.945605s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 0.950728s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.955907s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.961143s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.966436s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.971789s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.977201s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 29 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 0.982674s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 28 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 0.988209s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 27 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 0.993807s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 0.999463s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 25 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.00519s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 24 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.01098s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 23 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.01684s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.02277s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 21 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.02877s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.03484s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 19 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.04098s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 18 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.0472s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.05349s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.05985s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.0663s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 14 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.07282s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 1.07942s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 12 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.08611s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 11 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.09288s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.09973s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 9 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.10667s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 8 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.1137s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.12082s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.12803s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 5 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.13534s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 4 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 1.14274s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 3 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.15024s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 2 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 7/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.15783s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 227067 Accumulated number of search nodes in root state: 719549 Used RAM: 344208 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 7 -- REWARD RECEIVED: -7 *********************************************** *********************************************** >>> STARTING ROUND 8 -- REMAINING TIME 177s *********************************************** *********************************************** Planning step 1/50 in round 8/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 1.16553s. THTS: Maximal search depth set to 50 Search time: 1.16554s Statistics of THTS: Performed trials: 62340 Created SearchNodes: 196336 Cache Hits: 25141 Action Selection: Exploitation in Root: 59956 Exploration in Root: 2384 Percentage Exploration in Root: 0.0382419 Skipped backups: 22857890 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42804 (in 62343 real visits) Q-Value Estimates: noop() : -5.39 (in 1199 real visits) move(x3, y2) : -16.4 (in 1199 real visits) move(x2, y1) : -4.42804 (in 59945 real visits) Used RAM: 348160 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 8/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 1 Setting time for this decision to 1.16552s. THTS: Maximal search depth set to 49 Search time: 1.16554s Statistics of THTS: Performed trials: 61755 Created SearchNodes: 193653 Cache Hits: 24454 Skipped backups: 24119768 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42804 (in 61759 real visits) Q-Value Estimates: noop() : -4.42804 (in 58261 real visits) move(x3, y1) : -5.4089 (in 1166 real visits) move(x2, y2) : -49 (in 1166 real visits) move(x1, y1) : -5.3711 (in 1166 real visits) Used RAM: 348160 Submitted action: noop() Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 8/10 Current state: 0 0 0 1 0 0 0 0 0 0 1 | 0 Setting time for this decision to 1.16551s. THTS: Maximal search depth set to 48 Search time: 1.16554s Statistics of THTS: Performed trials: 63774 Created SearchNodes: 198355 Cache Hits: 26811 Skipped backups: 25448622 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 63778 real visits) Q-Value Estimates: noop() : -4.4089 (in 1204 real visits) move(x3, y1) : -5.38433 (in 1204 real visits) move(x2, y2) : -3 (in 60166 real visits) move(x1, y1) : -5 (in 1204 real visits) Used RAM: 348424 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 8/10 Current state: 0 0 0 0 1 0 0 0 0 1 0 | 0 Setting time for this decision to 1.16549s. THTS: Maximal search depth set to 47 Search time: 1.16552s Statistics of THTS: Performed trials: 64220 Created SearchNodes: 198443 Cache Hits: 27376 Skipped backups: 26809940 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 64225 real visits) Q-Value Estimates: noop() : -3 (in 1190 real visits) move(x3, y2) : -15.5 (in 1190 real visits) move(x2, y3) : -2 (in 59465 real visits) move(x2, y1) : -4.4089 (in 1190 real visits) move(x1, y2) : -4 (in 1190 real visits) Used RAM: 348424 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 8/10 Current state: 0 0 0 0 0 1 0 0 0 0 0 | 0 Setting time for this decision to 1.16547s. THTS: Maximal search depth set to 46 Search time: 1.16548s Statistics of THTS: Performed trials: 64634 Created SearchNodes: 199650 Cache Hits: 27827 Skipped backups: 28209760 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 64638 real visits) Q-Value Estimates: noop() : -2 (in 62149 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 1243 real visits) move(x1, y3) : -3 (in 1243 real visits) Used RAM: 348424 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 6/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.16546s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.17349s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.18168s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 43 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.18998s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 42 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 1.19839s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 41 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.20693s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.21559s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.22437s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 38 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.23328s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.24233s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 36 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.2515s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 35 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.26082s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.27028s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.27987s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.28962s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.29952s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 30 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.30957s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 29 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.31977s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 28 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.33013s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.34067s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.35136s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.36223s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.37328s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 23 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.38451s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 22 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.39593s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 21 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.40753s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 20 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 1.41933s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 19 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.43133s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 18 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.44354s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.45595s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.46858s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 15 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.48144s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 14 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.49452s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.50783s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 12 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.52139s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 11 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.53519s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.54924s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 9 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 1.56356s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 8 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 1.57814s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.59299s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.60813s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.62357s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 4 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.63929s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.65533s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 2 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 8/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.67169s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 289407 Accumulated number of search nodes in root state: 915885 Used RAM: 348424 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 8 -- REWARD RECEIVED: -5 *********************************************** *********************************************** >>> STARTING ROUND 9 -- REMAINING TIME 171s *********************************************** *********************************************** Planning step 1/50 in round 9/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 1.68837s. THTS: Maximal search depth set to 50 Search time: 1.68838s Statistics of THTS: Performed trials: 88828 Created SearchNodes: 278131 Cache Hits: 36107 Action Selection: Exploitation in Root: 85419 Exploration in Root: 3409 Percentage Exploration in Root: 0.0383775 Skipped backups: 30127060 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42775 (in 88831 real visits) Q-Value Estimates: noop() : -5.4008 (in 1709 real visits) move(x3, y2) : -16.4 (in 1709 real visits) move(x2, y1) : -4.42775 (in 85413 real visits) Used RAM: 356608 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 9/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 1.68835s. THTS: Maximal search depth set to 49 Search time: 1.68836s Statistics of THTS: Performed trials: 90473 Created SearchNodes: 280335 Cache Hits: 38135 Skipped backups: 32092042 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 90477 real visits) Q-Value Estimates: noop() : -4.417 (in 1708 real visits) move(x3, y1) : -5.39 (in 1708 real visits) move(x2, y2) : -3 (in 85353 real visits) move(x1, y1) : -5 (in 1708 real visits) Used RAM: 356872 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 9/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 1 Setting time for this decision to 1.68833s. THTS: Maximal search depth set to 48 Search time: 1.68835s Statistics of THTS: Performed trials: 90328 Created SearchNodes: 276267 Cache Hits: 37893 Skipped backups: 34089960 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 90333 real visits) Q-Value Estimates: noop() : -48 (in 1673 real visits) move(x3, y2) : -15.8 (in 1673 real visits) move(x2, y3) : -2 (in 83641 real visits) move(x2, y1) : -4.417 (in 1673 real visits) move(x1, y2) : -4 (in 1673 real visits) Used RAM: 356872 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 9/10 Current state: 0 0 0 0 0 1 0 0 0 0 1 | 0 Setting time for this decision to 1.68831s. THTS: Maximal search depth set to 47 Search time: 1.68833s Statistics of THTS: Performed trials: 91487 Created SearchNodes: 282079 Cache Hits: 39344 Skipped backups: 36152904 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 91491 real visits) Q-Value Estimates: noop() : -2 (in 87968 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 1760 real visits) move(x1, y3) : -3 (in 1760 real visits) Used RAM: 356872 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.68829s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 46 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.70594s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 45 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.72404s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 44 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.74254s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.76143s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 42 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.78075s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 41 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.80049s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.82069s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 39 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.84133s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 1.86245s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 37 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 1.88406s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 36 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 1.90618s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.92882s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.95201s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 1.97578s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.00012s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 31 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 2.02508s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 30 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 2.05066s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 29 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 2.0769s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 28 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 2.10383s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 27 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 2.13146s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 2.15983s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 25 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 2.18896s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 2.21889s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 23 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.24967s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 2.2813s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 21 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 2.31383s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 20 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 2.3473s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 19 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 2.38176s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 18 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 2.41725s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 2.45383s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.49152s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.53039s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 14 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.57049s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.61189s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 12 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 2.65466s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 11 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 2.69883s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 2.74451s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 9 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.79176s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 8 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 2.84068s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 7 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 2.89134s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 6 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 2.94384s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 2.99828s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 4 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 3.05477s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 3.11344s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 9/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 3.17443s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 378235 Accumulated number of search nodes in root state: 1194016 Used RAM: 356872 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 9 -- REWARD RECEIVED: -4 *********************************************** *********************************************** >>> STARTING ROUND 10 -- REMAINING TIME 164s *********************************************** *********************************************** Planning step 1/50 in round 10/10 Current state: 0 0 0 0 0 0 1 0 0 0 0 | 0 Setting time for this decision to 3.23782s. THTS: Maximal search depth set to 50 Search time: 3.23783s Statistics of THTS: Performed trials: 165277 Created SearchNodes: 515500 Cache Hits: 67396 Action Selection: Exploitation in Root: 158942 Exploration in Root: 6335 Percentage Exploration in Root: 0.0383296 Skipped backups: 39977400 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42826 (in 165280 real visits) Q-Value Estimates: noop() : -5.40323 (in 3179 real visits) move(x3, y2) : -16.4 (in 3179 real visits) move(x2, y1) : -4.42826 (in 158922 real visits) Used RAM: 380896 Submitted action: move(x2, y1) Immediate reward: -1 *********************************************** *********************************************** Planning step 2/50 in round 10/10 Current state: 0 0 0 1 0 0 0 0 0 0 0 | 0 Setting time for this decision to 3.23778s. THTS: Maximal search depth set to 49 Search time: 3.23779s Statistics of THTS: Performed trials: 166744 Created SearchNodes: 515881 Cache Hits: 70098 Skipped backups: 43860312 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 166748 real visits) Q-Value Estimates: noop() : -4.41457 (in 3147 real visits) move(x3, y1) : -5.4089 (in 3147 real visits) move(x2, y2) : -3 (in 157307 real visits) move(x1, y1) : -5 (in 3147 real visits) Used RAM: 380896 Submitted action: move(x2, y2) Immediate reward: -1 *********************************************** *********************************************** Planning step 3/50 in round 10/10 Current state: 0 0 0 0 1 0 0 0 0 0 0 | 0 Setting time for this decision to 3.23773s. THTS: Maximal search depth set to 48 Search time: 3.23773s Statistics of THTS: Performed trials: 167003 Created SearchNodes: 514169 Cache Hits: 70899 Skipped backups: 47801196 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 167008 real visits) Q-Value Estimates: noop() : -3 (in 3093 real visits) move(x3, y2) : -15.8 (in 3093 real visits) move(x2, y3) : -2 (in 154636 real visits) move(x2, y1) : -4.417 (in 3093 real visits) move(x1, y2) : -4 (in 3093 real visits) Used RAM: 380896 Submitted action: move(x2, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 4/50 in round 10/10 Current state: 0 0 0 0 0 1 0 0 0 0 0 | 1 Setting time for this decision to 3.2377s. THTS: Maximal search depth set to 47 Search time: 3.23773s Statistics of THTS: Performed trials: 166063 Created SearchNodes: 507509 Cache Hits: 69731 Skipped backups: 51814626 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 166067 real visits) Q-Value Estimates: noop() : -2 (in 159676 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -47 (in 3194 real visits) move(x1, y3) : -3 (in 3194 real visits) Used RAM: 380896 Submitted action: move(x3, y3) Immediate reward: -1 *********************************************** *********************************************** Planning step 5/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 3.23765s. THTS: Maximal search depth set to 46 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 46 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 6/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 3.30913s. THTS: Maximal search depth set to 45 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 45 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 7/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 3.38423s. THTS: Maximal search depth set to 44 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 44 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 8/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 3.46279s. THTS: Maximal search depth set to 43 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 43 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 9/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 3.54512s. THTS: Maximal search depth set to 42 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 42 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 10/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 3.63144s. THTS: Maximal search depth set to 41 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 41 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 11/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 3.7221s. THTS: Maximal search depth set to 40 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 40 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 12/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 3.81741s. THTS: Maximal search depth set to 39 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 39 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 13/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 3.91771s. THTS: Maximal search depth set to 38 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 38 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 14/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 4.02346s. THTS: Maximal search depth set to 37 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 37 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 15/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 4.13508s. THTS: Maximal search depth set to 36 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 36 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 16/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 4.25309s. THTS: Maximal search depth set to 35 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 35 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 17/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 4.378s. THTS: Maximal search depth set to 34 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 34 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 18/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 4.51052s. THTS: Maximal search depth set to 33 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 33 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 19/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 4.65131s. THTS: Maximal search depth set to 32 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 32 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 20/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 4.80116s. THTS: Maximal search depth set to 31 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 31 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 21/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 4.96103s. THTS: Maximal search depth set to 30 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 30 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 22/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 1 Setting time for this decision to 5.1319s. THTS: Maximal search depth set to 29 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 29 StateHashKey: 3840 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 23/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 5.31496s. THTS: Maximal search depth set to 28 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 28 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 24/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 5.51163s. THTS: Maximal search depth set to 27 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 27 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 25/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 5.72338s. THTS: Maximal search depth set to 26 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 26 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 26/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 5.95212s. THTS: Maximal search depth set to 25 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 25 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 27/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 6.19992s. THTS: Maximal search depth set to 24 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 24 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 28/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 6.46922s. THTS: Maximal search depth set to 23 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 23 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 29/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 6.76305s. THTS: Maximal search depth set to 22 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 22 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 30/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 7.08486s. THTS: Maximal search depth set to 21 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 21 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 31/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 7.4388s. THTS: Maximal search depth set to 20 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 20 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 32/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 7.83005s. THTS: Maximal search depth set to 19 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 19 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 33/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 8.26478s. THTS: Maximal search depth set to 18 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 18 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 34/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 8.75059s. THTS: Maximal search depth set to 17 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 17 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 35/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 9.29719s. THTS: Maximal search depth set to 16 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 16 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 36/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 9.91667s. THTS: Maximal search depth set to 15 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 15 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 37/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 10.6246s. THTS: Maximal search depth set to 14 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 14 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 38/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 11.4415s. THTS: Maximal search depth set to 13 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 13 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 39/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 12.3945s. THTS: Maximal search depth set to 12 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 12 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 40/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 1 Setting time for this decision to 13.5207s. THTS: Maximal search depth set to 11 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 11 StateHashKey: 2304 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 41/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 14.8723s. THTS: Maximal search depth set to 10 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 10 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 42/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 16.5241s. THTS: Maximal search depth set to 9 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 9 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 43/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 1 Setting time for this decision to 18.589s. THTS: Maximal search depth set to 8 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 1 Remaining Steps: 8 StateHashKey: 3328 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 44/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 1 | 0 Setting time for this decision to 21.2437s. THTS: Maximal search depth set to 7 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 7 StateHashKey: 1792 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 45/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 1 Setting time for this decision to 24.7835s. THTS: Maximal search depth set to 6 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 1 Remaining Steps: 6 StateHashKey: 2816 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 46/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 1 | 0 Setting time for this decision to 29.7392s. THTS: Maximal search depth set to 5 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 1 obstacle-at(x3, y2): 0 Remaining Steps: 5 StateHashKey: 1280 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 47/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 1 0 | 0 Setting time for this decision to 37.1728s. THTS: Maximal search depth set to 4 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 1 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 4 StateHashKey: 768 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 48/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 49.5617s. THTS: Maximal search depth set to 3 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 3 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 49/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 74.34s. THTS: Maximal search depth set to 2 Current root state is a reward lock state! agent-at(x1, y1): 0 agent-at(x1, y2): 0 agent-at(x1, y3): 0 agent-at(x2, y1): 0 agent-at(x2, y2): 0 agent-at(x2, y3): 0 agent-at(x3, y1): 0 agent-at(x3, y2): 0 agent-at(x3, y3): 1 obstacle-at(x1, y2): 0 obstacle-at(x2, y2): 0 obstacle-at(x3, y2): 0 Remaining Steps: 2 StateHashKey: 256 Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** Planning step 50/50 in round 10/10 Current state: 0 0 0 0 0 0 0 0 1 0 0 | 0 Setting time for this decision to 148.675s. THTS: Maximal search depth set to 1 Returning the optimal last action! Returning unique policy: noop() Statistics of THTS: Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: ROUND FINISHED Accumulated number of remaining steps in first solved root state: 0 Accumulated number of trials in root state: 543512 Accumulated number of search nodes in root state: 1709516 Used RAM: 380896 Submitted action: noop() Immediate reward: 0 *********************************************** *********************************************** >>> END OF ROUND 10 -- REWARD RECEIVED: -4 *********************************************** *********************************************** Immediate rewards: Round 0: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 Round 1: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 Round 2: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 Round 3: -1 -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -5 Round 4: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 Round 5: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 Round 6: -1 -1 -1 -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -7 Round 7: -1 -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -5 Round 8: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 Round 9: -1 -1 -1 -1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 = -4 >>> TOTAL REWARD: -45 >>> AVERAGE REWARD: -4.5 *********************************************** PROST complete running time: 92.5195s