/home/linuxbuildslave/buildslaves/ailinux/ipc-prob-build-singularity-linux/build/tmpKMjgMB /home/linuxbuildslave/buildslaves/ailinux/ipc-prob-build-singularity-linux/build/tmpKMjgMB *************** RDDL-PARSER CALL WITH 600SEC *************** Parsing... Setting outcome pruning to 0.5 ...finished (0.00115204s). instantiating... Instantiating variables... ...finished (6.50883e-05) Instantiating CPFs... ...finished (0.00019002) Instantiating preconditions... ...finished (0.000847101) ...finished (0.00111699s). preprocessing... Preparing evaluatables... ...finished (0.000957966) Preparing actions... ...finished (0.000134945) Calculating CPF domain... ...finished (0.000407934) Finalizing evaluatables... ...finished (0.000110865) Computing determinization... ...finished (2.14577e-06) Determining task properties... ...finished (1.90735e-06) Preparing hash keys... ...finished (6.10352e-05) Precomputing evaluatables... ...finished (0.000966072) Calculating min and max reward... ...finished (1.90735e-06) ...finished (0.00267816s). analyzing task... Creating training set with 56 candidates. ...finished (0.025187s). writing output for instance crossing_traffic_demo_inst_mdp__1... ...finished (0.0203862s). writing transition relations to json file... ...finished (0.00147319s). total time: 0.052036s RDDL-Parser took: 0.0595002s learning... THTS: learning... DD_Heuristic: learning [25s (0.125%)] with /home/linuxbuildslave/buildslaves/ailinux/ipc-prob-build-singularity-linux/build/tmpKMjgMB/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))))" }, "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))))" }, "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))))" }, "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))))" }, "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))))" }, "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))))" }, "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))))" }, "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))))" }, "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))))" }, "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))))" } }, "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: 0.13 => Time left: 24.87s move(x1, y2) ......overall time: 0.25 => Time left: 24.75s move(x1, y3) ......overall time: 0.37 => Time left: 24.63s move(x2, y1) ......overall time: 0.5 => Time left: 24.5s move(x2, y2) ......overall time: 0.63 => Time left: 24.37s move(x2, y3) ......overall time: 0.75 => Time left: 24.25s move(x3, y1) ......overall time: 0.87 => Time left: 24.13s move(x3, y2) ......overall time: 1 => Time left: 24s move(x3, y3) ......overall time: 1.12 => Time left: 23.88s noop......overall time: 1.24 => Time left: 23.76s Plan step 1/50... ...worst value: 1 ...overall worst value: 1 ...overall time: 1.24 => Time left: 23.76s Plan step 2/50... ...worst value: 2 ...overall worst value: 2 ...overall time: 1.24 => Time left: 23.76s Plan step 3/50... ...worst value: 3 ...overall worst value: 3 ...overall time: 1.24 => Time left: 23.76s Plan step 4/50... ...worst value: 4 ...overall worst value: 4 ...overall time: 1.24 => Time left: 23.76s Plan step 5/50... ...worst value: 5 ...overall worst value: 5 ...overall time: 1.25 => Time left: 23.75s Plan step 6/50... ...worst value: 6 ...overall worst value: 6 ...overall time: 1.25 => Time left: 23.75s Plan step 7/50... ...worst value: 7 ...overall worst value: 7 ...overall time: 1.25 => Time left: 23.75s Plan step 8/50... ...worst value: 8 ...overall worst value: 8 ...overall time: 1.25 => Time left: 23.75s Plan step 9/50... ...worst value: 9 ...overall worst value: 9 ...overall time: 1.25 => Time left: 23.75s Plan step 10/50... ...worst value: 10 ...overall worst value: 10 ...overall time: 1.25 => Time left: 23.75s Plan step 11/50... ...worst value: 11 ...overall worst value: 11 ...overall time: 1.25 => Time left: 23.75s Plan step 12/50... ...worst value: 12 ...overall worst value: 12 ...overall time: 1.25 => Time left: 23.75s Plan step 13/50... ...worst value: 13 ...overall worst value: 13 ...overall time: 1.25 => Time left: 23.75s Plan step 14/50... ...worst value: 14 ...overall worst value: 14 ...overall time: 1.25 => Time left: 23.75s Plan step 15/50... ...worst value: 15 ...overall worst value: 15 ...overall time: 1.25 => Time left: 23.75s Plan step 16/50... ...worst value: 16 ...overall worst value: 16 ...overall time: 1.25 => Time left: 23.75s Plan step 17/50... ...worst value: 17 ...overall worst value: 17 ...overall time: 1.25 => Time left: 23.75s Plan step 18/50... ...worst value: 18 ...overall worst value: 18 ...overall time: 1.25 => Time left: 23.75s Plan step 19/50... ...worst value: 19 ...overall worst value: 19 ...overall time: 1.25 => Time left: 23.75s Plan step 20/50... ...worst value: 20 ...overall worst value: 20 ...overall time: 1.25 => Time left: 23.75s Plan step 21/50... ...worst value: 21 ...overall worst value: 21 ...overall time: 1.25 => Time left: 23.75s Plan step 22/50... ...worst value: 22 ...overall worst value: 22 ...overall time: 1.25 => Time left: 23.75s Plan step 23/50... ...worst value: 23 ...overall worst value: 23 ...overall time: 1.25 => Time left: 23.75s Plan step 24/50... ...worst value: 24 ...overall worst value: 24 ...overall time: 1.25 => Time left: 23.75s Plan step 25/50... ...worst value: 25 ...overall worst value: 25 ...overall time: 1.25 => Time left: 23.75s Plan step 26/50... ...worst value: 26 ...overall worst value: 26 ...overall time: 1.26 => Time left: 23.74s Plan step 27/50... ...worst value: 27 ...overall worst value: 27 ...overall time: 1.26 => Time left: 23.74s Plan step 28/50... ...worst value: 28 ...overall worst value: 28 ...overall time: 1.26 => Time left: 23.74s Plan step 29/50... ...worst value: 29 ...overall worst value: 29 ...overall time: 1.26 => Time left: 23.74s Plan step 30/50... ...worst value: 30 ...overall worst value: 30 ...overall time: 1.26 => Time left: 23.74s Plan step 31/50... ...worst value: 31 ...overall worst value: 31 ...overall time: 1.26 => Time left: 23.74s Plan step 32/50... ...worst value: 32 ...overall worst value: 32 ...overall time: 1.26 => Time left: 23.74s Plan step 33/50... ...worst value: 33 ...overall worst value: 33 ...overall time: 1.26 => Time left: 23.74s Plan step 34/50... ...worst value: 34 ...overall worst value: 34 ...overall time: 1.26 => Time left: 23.74s Plan step 35/50... ...worst value: 35 ...overall worst value: 35 ...overall time: 1.27 => Time left: 23.73s Plan step 36/50... ...worst value: 36 ...overall worst value: 36 ...overall time: 1.27 => Time left: 23.73s Plan step 37/50... ...worst value: 37 ...overall worst value: 37 ...overall time: 1.27 => Time left: 23.73s Plan step 38/50... ...worst value: 38 ...overall worst value: 38 ...overall time: 1.27 => Time left: 23.73s Plan step 39/50... ...worst value: 39 ...overall worst value: 39 ...overall time: 1.27 => Time left: 23.73s Plan step 40/50... ...worst value: 40 ...overall worst value: 40 ...overall time: 1.27 => Time left: 23.73s Plan step 41/50... ...worst value: 41 ...overall worst value: 41 ...overall time: 1.27 => Time left: 23.73s Plan step 42/50... ...worst value: 42 ...overall worst value: 42 ...overall time: 1.27 => Time left: 23.73s Plan step 43/50... ...worst value: 43 ...overall worst value: 43 ...overall time: 1.27 => Time left: 23.73s Plan step 44/50... ...worst value: 44 ...overall worst value: 44 ...overall time: 1.27 => Time left: 23.73s Plan step 45/50... ...worst value: 45 ...overall worst value: 45 ...overall time: 1.27 => Time left: 23.73s Plan step 46/50... ...worst value: 46 ...overall worst value: 46 ...overall time: 1.27 => Time left: 23.73s Plan step 47/50... ...worst value: 47 ...overall worst value: 47 ...overall time: 1.27 => Time left: 23.73s Plan step 48/50... ...worst value: 48 ...overall worst value: 48 ...overall time: 1.27 => Time left: 23.73s Plan step 49/50... ...worst value: 49 ...overall worst value: 49 ...overall time: 1.27 => Time left: 23.73s Plan step 50/50... ...worst value: 50 ...overall worst value: 50 ...overall time: 1.27 => Time left: 23.73s Completed layers: 51 Reset Det Task. ... finished THTS: ...finished ...finished (1.35493s). 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 0.39105s. THTS: Maximal search depth set to 50 Search time: 0.391076s Statistics of THTS: Performed trials: 20588 Created SearchNodes: 65747 Cache Hits: 7972 Action Selection: Exploitation in Root: 19811 Exploration in Root: 777 Percentage Exploration in Root: 0.0377404 Skipped backups: 366086 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42583 (in 20591 real visits) Q-Value Estimates: noop() : -5.336 (in 396 real visits) move(x3, y2) : -16.4 (in 396 real visits) move(x2, y1) : -4.42583 (in 19799 real visits) Used RAM: 334772 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 0.391046s. THTS: Maximal search depth set to 49 Search time: 0.391073s Statistics of THTS: Performed trials: 22599 Created SearchNodes: 70852 Cache Hits: 9452 Skipped backups: 777474 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 22603 real visits) Q-Value Estimates: noop() : -4.363 (in 427 real visits) move(x3, y1) : -5.3441 (in 427 real visits) move(x2, y2) : -3 (in 21322 real visits) move(x1, y1) : -5 (in 427 real visits) Used RAM: 335296 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 0.391042s. THTS: Maximal search depth set to 48 Search time: 0.391061s Statistics of THTS: Performed trials: 22772 Created SearchNodes: 70278 Cache Hits: 9533 Skipped backups: 1201832 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 22777 real visits) Q-Value Estimates: noop() : -48 (in 422 real visits) move(x3, y2) : -15.8 (in 422 real visits) move(x2, y3) : -2 (in 21089 real visits) move(x2, y1) : -4.363 (in 422 real visits) move(x1, y2) : -4 (in 422 real visits) Used RAM: 335296 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 0.391038s. THTS: Maximal search depth set to 47 Search time: 0.391042s Statistics of THTS: Performed trials: 22973 Created SearchNodes: 70541 Cache Hits: 9803 Skipped backups: 1642694 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 22977 real visits) Q-Value Estimates: noop() : -2 (in 22090 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -47 (in 442 real visits) move(x1, y3) : -3 (in 442 real visits) Used RAM: 335552 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 0.391034s. 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: 335552 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 0.391814s. 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: 335552 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 0.392601s. 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: 335552 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 0.393391s. 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: 335552 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 0.394187s. 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: 335552 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 0.394984s. 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: 335552 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 0.395786s. 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: 335552 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 0.396589s. 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: 335552 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 0.397398s. 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: 335552 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 0.398207s. 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: 335552 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 0.399023s. 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: 335552 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 0.399839s. 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: 335552 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 0.400659s. 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: 335552 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 0.401484s. 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: 335552 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 0.402313s. 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: 335552 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 0.403141s. 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: 335552 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 0.403975s. 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: 335552 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 0.404812s. 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: 335552 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 0.405655s. 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: 335552 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 0.406499s. 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: 335552 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 0.407349s. 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: 335552 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 0.4082s. 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: 335552 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 0.409057s. 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: 335552 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 0.409915s. 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: 335552 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 0.410778s. 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: 335552 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 0.411643s. 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: 335552 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 0.412511s. 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: 335552 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 0.413386s. 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: 335552 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 0.414265s. 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: 335552 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 0.415146s. 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: 335552 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 0.416032s. 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: 335552 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 0.416923s. 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: 335552 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 0.417813s. 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: 335552 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 0.418711s. 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: 335552 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 0.419613s. 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: 335552 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 0.420516s. 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: 335552 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 0.421426s. 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: 335552 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 0.422338s. 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: 335552 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 0.423255s. 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: 335552 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 0.424175s. 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: 335552 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 0.425101s. 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: 335552 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 0.426029s. 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: 335552 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 0.426963s. 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: 335552 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 0.427901s. 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: 335552 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 0.428841s. 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: 335552 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 0.429785s. 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: 20588 Accumulated number of search nodes in root state: 65747 Used RAM: 335552 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 0.430736s. THTS: Maximal search depth set to 50 Search time: 0.430743s Statistics of THTS: Performed trials: 24588 Created SearchNodes: 78113 Cache Hits: 9783 Action Selection: Exploitation in Root: 23650 Exploration in Root: 938 Percentage Exploration in Root: 0.0381487 Skipped backups: 2091848 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 24591 real visits) Q-Value Estimates: noop() : -5.3441 (in 473 real visits) move(x3, y2) : -16.4 (in 473 real visits) move(x2, y1) : -4.42753 (in 23645 real visits) Used RAM: 336304 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 0.430731s. THTS: Maximal search depth set to 49 Search time: 0.430739s Statistics of THTS: Performed trials: 24860 Created SearchNodes: 77609 Cache Hits: 10440 Skipped backups: 2549936 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 24864 real visits) Q-Value Estimates: noop() : -4.3 (in 470 real visits) move(x3, y1) : -5.3441 (in 470 real visits) move(x2, y2) : -3 (in 23454 real visits) move(x1, y1) : -5 (in 470 real visits) Used RAM: 336304 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 0.430725s. THTS: Maximal search depth set to 48 Search time: 0.430728s Statistics of THTS: Performed trials: 25266 Created SearchNodes: 77741 Cache Hits: 10658 Skipped backups: 3027742 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 25271 real visits) Q-Value Estimates: noop() : -48 (in 468 real visits) move(x3, y2) : -15.8 (in 468 real visits) move(x2, y3) : -2 (in 23399 real visits) move(x2, y1) : -4.39 (in 468 real visits) move(x1, y2) : -4 (in 468 real visits) Used RAM: 336304 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 0.430723s. THTS: Maximal search depth set to 47 Search time: 0.430758s Statistics of THTS: Performed trials: 25387 Created SearchNodes: 77873 Cache Hits: 10832 Skipped backups: 3520362 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 25391 real visits) Q-Value Estimates: noop() : -2 (in 24410 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -47 (in 489 real visits) move(x1, y3) : -3 (in 489 real visits) Used RAM: 336304 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 0.430717s. 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: 336304 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 0.431676s. 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: 336304 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 0.432642s. 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: 336304 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 0.433614s. 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: 336304 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 0.434588s. 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: 336304 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 0.435567s. 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: 336304 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 0.436552s. 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: 336304 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 0.43754s. 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: 336304 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 0.438534s. 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: 336304 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 0.439531s. 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: 336304 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 0.440534s. 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: 336304 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 0.44154s. 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: 336304 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 0.442553s. 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: 336304 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 0.443568s. 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: 336304 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 0.44459s. 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: 336304 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 0.445615s. 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: 336304 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 0.446647s. 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: 336304 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 0.447681s. 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: 336304 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 0.448722s. 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: 336304 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 0.449766s. 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: 336304 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 0.450815s. 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: 336304 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 0.451871s. 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: 336304 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 0.452929s. 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: 336304 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 0.453995s. 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: 336304 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 0.455066s. 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: 336304 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 0.45614s. 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: 336304 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 0.457219s. 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: 336304 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 0.458305s. 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: 336304 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 0.459395s. 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: 336304 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 0.460492s. 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: 336304 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 0.461594s. 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: 336304 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 0.462699s. 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: 336304 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 0.463812s. 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: 336304 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 0.464927s. 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: 336304 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 0.466051s. 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: 336304 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 0.467175s. 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: 336304 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 0.46831s. 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: 336304 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 0.469447s. 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: 336304 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 0.470593s. 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: 336304 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 0.471742s. 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: 336304 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 0.472899s. 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: 336304 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 0.474059s. 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: 336304 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 0.475228s. 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: 336304 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 0.4764s. 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: 336304 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 0.47758s. 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: 336304 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 0.478763s. 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: 45176 Accumulated number of search nodes in root state: 143860 Used RAM: 336304 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 0.479955s. THTS: Maximal search depth set to 50 Search time: 0.479971s Statistics of THTS: Performed trials: 26889 Created SearchNodes: 85510 Cache Hits: 10642 Action Selection: Exploitation in Root: 25869 Exploration in Root: 1020 Percentage Exploration in Root: 0.0379337 Skipped backups: 4016704 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.4268 (in 26892 real visits) Q-Value Estimates: noop() : -5.3189 (in 518 real visits) move(x3, y2) : -16.4 (in 518 real visits) move(x2, y1) : -4.4268 (in 25856 real visits) Used RAM: 336828 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 0.47995s. THTS: Maximal search depth set to 49 Search time: 0.479977s Statistics of THTS: Performed trials: 27472 Created SearchNodes: 86097 Cache Hits: 11463 Skipped backups: 4530838 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 27476 real visits) Q-Value Estimates: noop() : -4.327 (in 519 real visits) move(x3, y1) : -5.3171 (in 519 real visits) move(x2, y2) : -3 (in 25919 real visits) move(x1, y1) : -5 (in 519 real visits) Used RAM: 337092 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 0.479945s. THTS: Maximal search depth set to 48 Search time: 0.479964s Statistics of THTS: Performed trials: 28128 Created SearchNodes: 87184 Cache Hits: 12058 Skipped backups: 5067208 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 28133 real visits) Q-Value Estimates: noop() : -3 (in 521 real visits) move(x3, y2) : -15.8 (in 521 real visits) move(x2, y3) : -2 (in 26049 real visits) move(x2, y1) : -4.39 (in 521 real visits) move(x1, y2) : -4 (in 521 real visits) Used RAM: 337092 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 0.47994s. THTS: Maximal search depth set to 47 Search time: 0.47995s Statistics of THTS: Performed trials: 28099 Created SearchNodes: 86881 Cache Hits: 12217 Skipped backups: 5617302 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 28103 real visits) Q-Value Estimates: noop() : -2 (in 27018 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 541 real visits) move(x1, y3) : -3 (in 541 real visits) Used RAM: 337092 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 0.479934s. 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: 337092 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 0.481139s. 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: 337092 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 0.482353s. 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: 337092 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 0.483575s. 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: 337092 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 0.484801s. 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: 337092 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 0.486036s. 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: 337092 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 0.487274s. 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: 337092 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 0.488519s. 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: 337092 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 0.489773s. 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: 337092 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 0.491031s. 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: 337092 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 0.492298s. 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: 337092 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 0.493569s. 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: 337092 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 0.494849s. 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: 337092 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 0.496133s. 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: 337092 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 0.497427s. 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: 337092 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 0.498724s. 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: 337092 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 0.500032s. 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: 337092 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 0.501343s. 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: 337092 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 0.502661s. 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: 337092 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 0.503989s. 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: 337092 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 0.505322s. 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: 337092 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 0.506664s. 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: 337092 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 0.508011s. 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: 337092 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 0.509367s. 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: 337092 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 0.510728s. 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: 337092 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 0.5121s. 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: 337092 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 0.513476s. 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: 337092 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 0.514862s. 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: 337092 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 0.516253s. 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: 337092 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 0.517654s. 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: 337092 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 0.51906s. 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: 337092 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 0.520474s. 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: 337092 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 0.521896s. 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: 337092 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 0.523328s. 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: 337092 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 0.524765s. 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: 337092 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 0.526213s. 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: 337092 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 0.527667s. 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: 337092 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 0.529128s. 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: 337092 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 0.530601s. 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: 337092 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 0.532078s. 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: 337092 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 0.533567s. 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: 337092 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 0.535062s. 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: 337092 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 0.536568s. 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: 337092 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 0.538079s. 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: 337092 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 0.539599s. 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: 337092 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 0.541131s. 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: 72065 Accumulated number of search nodes in root state: 229370 Used RAM: 337092 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 0.542669s. THTS: Maximal search depth set to 50 Search time: 0.542692s Statistics of THTS: Performed trials: 30249 Created SearchNodes: 95917 Cache Hits: 12052 Action Selection: Exploitation in Root: 29096 Exploration in Root: 1153 Percentage Exploration in Root: 0.038117 Skipped backups: 6185648 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42731 (in 30252 real visits) Q-Value Estimates: noop() : -5.363 (in 582 real visits) move(x3, y2) : -16.4 (in 582 real visits) move(x2, y1) : -4.42731 (in 29088 real visits) Used RAM: 338148 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 0.542662s. THTS: Maximal search depth set to 49 Search time: 0.542682s Statistics of THTS: Performed trials: 29745 Created SearchNodes: 94345 Cache Hits: 11570 Skipped backups: 6737908 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42583 (in 29749 real visits) Q-Value Estimates: noop() : -4.42583 (in 28063 real visits) move(x3, y1) : -5.3171 (in 562 real visits) move(x2, y2) : -49 (in 562 real visits) move(x1, y1) : -5.363 (in 562 real visits) Used RAM: 338148 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 0.542658s. THTS: Maximal search depth set to 48 Search time: 0.542661s Statistics of THTS: Performed trials: 31034 Created SearchNodes: 97052 Cache Hits: 13023 Skipped backups: 7328586 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 31038 real visits) Q-Value Estimates: noop() : -4.39 (in 586 real visits) move(x3, y1) : -5.3441 (in 586 real visits) move(x2, y2) : -3 (in 29280 real visits) move(x1, y1) : -5 (in 586 real visits) Used RAM: 338148 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 0.542651s. THTS: Maximal search depth set to 47 Search time: 0.542656s Statistics of THTS: Performed trials: 31313 Created SearchNodes: 96993 Cache Hits: 13413 Skipped backups: 7934674 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 31318 real visits) Q-Value Estimates: noop() : -3 (in 580 real visits) move(x3, y2) : -15.5 (in 580 real visits) move(x2, y3) : -2 (in 28998 real visits) move(x2, y1) : -4.39 (in 580 real visits) move(x1, y2) : -4 (in 580 real visits) Used RAM: 338148 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 0.542647s. THTS: Maximal search depth set to 46 Search time: 0.542659s Statistics of THTS: Performed trials: 31437 Created SearchNodes: 97143 Cache Hits: 13643 Skipped backups: 8557594 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 31441 real visits) Q-Value Estimates: noop() : -2 (in 30228 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 605 real visits) move(x1, y3) : -3 (in 605 real visits) Used RAM: 338148 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 0.542641s. 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: 338148 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 0.544203s. 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: 338148 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 0.545784s. 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: 338148 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 0.547371s. 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: 338148 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 0.548968s. 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: 338148 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 0.550576s. 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: 338148 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 0.552192s. 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: 338148 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 0.553817s. 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: 338148 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 0.555454s. 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: 338148 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 0.557098s. 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: 338148 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 0.558755s. 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: 338148 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 0.560419s. 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: 338148 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 0.562096s. 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: 338148 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 0.56378s. 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: 338148 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 0.565474s. 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: 338148 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 0.567179s. 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: 338148 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 0.568897s. 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: 338148 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 0.570622s. 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: 338148 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 0.572361s. 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: 338148 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 0.574107s. 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: 338148 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 0.575865s. 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: 338148 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 0.577636s. 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: 338148 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 0.579415s. 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: 338148 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 0.581205s. 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: 338148 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 0.583009s. 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: 338148 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 0.584822s. 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: 338148 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 0.586646s. 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: 338148 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 0.588484s. 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: 338148 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 0.590331s. 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: 338148 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 0.592193s. 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: 338148 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 0.594063s. 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: 338148 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 0.595949s. 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: 338148 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 0.597843s. 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: 338148 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 0.59975s. 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: 338148 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 0.601672s. 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: 338148 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 0.603603s. 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: 338148 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 0.605547s. 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: 338148 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 0.607506s. 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: 338148 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 0.609476s. 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: 338148 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 0.611461s. 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: 338148 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 0.613456s. 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: 338148 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 0.615464s. 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: 338148 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 0.617488s. 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: 338148 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 0.619523s. 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: 338148 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 0.621571s. 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: 102314 Accumulated number of search nodes in root state: 325287 Used RAM: 338148 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 0.623633s. THTS: Maximal search depth set to 50 Search time: 0.623655s Statistics of THTS: Performed trials: 34317 Created SearchNodes: 108802 Cache Hits: 13704 Action Selection: Exploitation in Root: 33007 Exploration in Root: 1310 Percentage Exploration in Root: 0.0381735 Skipped backups: 9214464 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 34320 real visits) Q-Value Estimates: noop() : -5.3441 (in 660 real visits) move(x3, y2) : -16.4 (in 660 real visits) move(x2, y1) : -4.42753 (in 33000 real visits) Used RAM: 339464 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 0.623629s. THTS: Maximal search depth set to 49 Search time: 0.623653s Statistics of THTS: Performed trials: 35443 Created SearchNodes: 110542 Cache Hits: 14916 Skipped backups: 9899520 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 35447 real visits) Q-Value Estimates: noop() : -4.39 (in 669 real visits) move(x3, y1) : -5.3441 (in 669 real visits) move(x2, y2) : -3 (in 33440 real visits) move(x1, y1) : -5 (in 669 real visits) Used RAM: 339464 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 0.623621s. THTS: Maximal search depth set to 48 Search time: 0.623632s Statistics of THTS: Performed trials: 35641 Created SearchNodes: 109519 Cache Hits: 14997 Skipped backups: 10604928 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 35646 real visits) Q-Value Estimates: noop() : -48 (in 661 real visits) move(x3, y2) : -15.8 (in 661 real visits) move(x2, y3) : -2 (in 33002 real visits) move(x2, y1) : -4.39 (in 661 real visits) move(x1, y2) : -4 (in 661 real visits) Used RAM: 339464 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 0.623613s. THTS: Maximal search depth set to 47 Search time: 0.623633s Statistics of THTS: Performed trials: 35929 Created SearchNodes: 110960 Cache Hits: 15591 Skipped backups: 11331008 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 35933 real visits) Q-Value Estimates: noop() : -2 (in 34548 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 691 real visits) move(x1, y3) : -3 (in 691 real visits) Used RAM: 339464 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 0.623608s. 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: 339464 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 0.625705s. 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: 339464 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 0.62782s. 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: 339464 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 0.629956s. 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: 339464 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 0.632103s. 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: 339464 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 0.634265s. 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: 339464 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 0.636441s. 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: 339464 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 0.638633s. 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: 339464 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 0.640844s. 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: 339464 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 0.643066s. 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: 339464 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 0.645304s. 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: 339464 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 0.647561s. 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: 339464 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 0.649831s. 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: 339464 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 0.652117s. 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: 339464 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 0.654422s. 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: 339464 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 0.65674s. 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: 339464 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 0.659075s. 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: 339464 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 0.66143s. 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: 339464 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 0.663799s. 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: 339464 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 0.666184s. 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: 339464 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 0.668591s. 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: 339464 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 0.671011s. 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: 339464 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 0.673449s. 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: 339464 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 0.675908s. 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: 339464 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 0.678382s. 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: 339464 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 0.680875s. 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: 339464 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 0.683389s. 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: 339464 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 0.685918s. 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: 339464 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 0.688466s. 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: 339464 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 0.691034s. 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: 339464 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 0.69362s. 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: 339464 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 0.696226s. 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: 339464 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 0.698856s. 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: 339464 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 0.701502s. 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: 339464 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 0.704168s. 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: 339464 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 0.706854s. 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: 339464 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 0.709565s. 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: 339464 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 0.712293s. 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: 339464 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 0.715043s. 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: 339464 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 0.717817s. 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: 339464 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 0.720609s. 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: 339464 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 0.723424s. 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: 339464 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 0.72626s. 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: 339464 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 0.729123s. 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: 339464 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 0.732004s. 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: 339464 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 0.734908s. 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: 136631 Accumulated number of search nodes in root state: 434089 Used RAM: 339464 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 0.737836s. THTS: Maximal search depth set to 50 Search time: 0.737844s Statistics of THTS: Performed trials: 39937 Created SearchNodes: 126282 Cache Hits: 15984 Action Selection: Exploitation in Root: 38432 Exploration in Root: 1505 Percentage Exploration in Root: 0.0376844 Skipped backups: 12108508 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 39940 real visits) Q-Value Estimates: noop() : -5.363 (in 769 real visits) move(x3, y2) : -16.4 (in 769 real visits) move(x2, y1) : -4.42753 (in 38402 real visits) Used RAM: 341124 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 0.737827s. THTS: Maximal search depth set to 49 Search time: 0.737833s Statistics of THTS: Performed trials: 41535 Created SearchNodes: 129499 Cache Hits: 17462 Skipped backups: 12929672 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 41539 real visits) Q-Value Estimates: noop() : -4.39 (in 784 real visits) move(x3, y1) : -5.3711 (in 784 real visits) move(x2, y2) : -3 (in 39187 real visits) move(x1, y1) : -5 (in 784 real visits) Used RAM: 341388 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 0.737819s. THTS: Maximal search depth set to 48 Search time: 0.737843s Statistics of THTS: Performed trials: 41838 Created SearchNodes: 129652 Cache Hits: 17852 Skipped backups: 13769408 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 41843 real visits) Q-Value Estimates: noop() : -3 (in 775 real visits) move(x3, y2) : -15.8 (in 775 real visits) move(x2, y3) : -2 (in 38743 real visits) move(x2, y1) : -4.417 (in 775 real visits) move(x1, y2) : -4 (in 775 real visits) Used RAM: 341652 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 0.73781s. THTS: Maximal search depth set to 47 Search time: 0.737836s Statistics of THTS: Performed trials: 42027 Created SearchNodes: 129799 Cache Hits: 18197 Skipped backups: 14634448 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 42031 real visits) Q-Value Estimates: noop() : -2 (in 40410 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 809 real visits) move(x1, y3) : -3 (in 809 real visits) Used RAM: 341652 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 0.737805s. 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: 341652 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 0.740792s. 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: 341652 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 0.743816s. 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: 341652 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 0.746864s. 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: 341652 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 0.749938s. 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: 341652 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 0.753037s. 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: 341652 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 0.756163s. 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: 341652 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 0.759314s. 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: 341652 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 0.762492s. 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: 341652 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 0.7657s. 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: 341652 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 0.768932s. 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: 341652 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 0.772191s. 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: 341652 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 0.775479s. 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: 341652 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 0.778794s. 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: 341652 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 0.782138s. 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: 341652 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 0.785515s. 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: 341652 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 0.788917s. 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: 341652 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 0.792349s. 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: 341652 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 0.795811s. 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: 341652 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 0.799304s. 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: 341652 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 0.802827s. 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: 341652 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 0.806382s. 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: 341652 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 0.809973s. 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: 341652 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 0.813592s. 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: 341652 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 0.817243s. 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: 341652 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 0.820928s. 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: 341652 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 0.824645s. 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: 341652 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 0.828397s. 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: 341652 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 0.832183s. 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: 341652 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 0.836005s. 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: 341652 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 0.839861s. 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: 341652 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 0.843758s. 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: 341652 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 0.847687s. 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: 341652 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 0.851653s. 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: 341652 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 0.855656s. 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: 341652 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 0.859697s. 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: 341652 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 0.863776s. 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: 341652 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 0.867895s. 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: 341652 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 0.872058s. 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: 341652 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 0.876256s. 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: 341652 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 0.880495s. 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: 341652 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 0.884776s. 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: 341652 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 0.889098s. 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: 341652 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 0.893463s. 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: 341652 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 0.897871s. 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: 341652 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 0.902323s. 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: 176568 Accumulated number of search nodes in root state: 560371 Used RAM: 341652 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 0.90682s. THTS: Maximal search depth set to 50 Search time: 0.906827s Statistics of THTS: Performed trials: 49244 Created SearchNodes: 155595 Cache Hits: 19732 Action Selection: Exploitation in Root: 47360 Exploration in Root: 1884 Percentage Exploration in Root: 0.0382585 Skipped backups: 15620036 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42804 (in 49247 real visits) Q-Value Estimates: noop() : -5.3711 (in 948 real visits) move(x3, y2) : -16.4 (in 948 real visits) move(x2, y1) : -4.42804 (in 47351 real visits) Used RAM: 344292 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 0.906809s. THTS: Maximal search depth set to 49 Search time: 0.906832s Statistics of THTS: Performed trials: 48714 Created SearchNodes: 153153 Cache Hits: 19196 Skipped backups: 16585904 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 48718 real visits) Q-Value Estimates: noop() : -4.42753 (in 45958 real visits) move(x3, y1) : -5.39567 (in 920 real visits) move(x2, y2) : -49 (in 920 real visits) move(x1, y1) : -5.3711 (in 920 real visits) Used RAM: 344292 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 0.906803s. THTS: Maximal search depth set to 48 Search time: 0.906827s Statistics of THTS: Performed trials: 48761 Created SearchNodes: 153322 Cache Hits: 19223 Skipped backups: 17553290 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42753 (in 48765 real visits) Q-Value Estimates: noop() : -4.42753 (in 46002 real visits) move(x3, y1) : -5.3189 (in 921 real visits) move(x2, y2) : -48 (in 921 real visits) move(x1, y1) : -5.37443 (in 921 real visits) Used RAM: 344292 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 0.906792s. THTS: Maximal search depth set to 47 Search time: 0.906798s Statistics of THTS: Performed trials: 48657 Created SearchNodes: 153265 Cache Hits: 19145 Skipped backups: 18518666 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42826 (in 48661 real visits) Q-Value Estimates: noop() : -4.42826 (in 45904 real visits) move(x3, y1) : -5.363 (in 919 real visits) move(x2, y2) : -47 (in 919 real visits) move(x1, y1) : -5.363 (in 919 real visits) Used RAM: 344292 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 0.906781s. THTS: Maximal search depth set to 46 Search time: 0.906825s Statistics of THTS: Performed trials: 50205 Created SearchNodes: 156468 Cache Hits: 21066 Skipped backups: 19533872 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 50209 real visits) Q-Value Estimates: noop() : -4.39 (in 948 real visits) move(x3, y1) : -5.3711 (in 948 real visits) move(x2, y2) : -3 (in 47365 real visits) move(x1, y1) : -5 (in 948 real visits) Used RAM: 344292 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 0.906774s. THTS: Maximal search depth set to 45 Search time: 0.906782s Statistics of THTS: Performed trials: 50514 Created SearchNodes: 156251 Cache Hits: 21571 Skipped backups: 20572480 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 50519 real visits) Q-Value Estimates: noop() : -3 (in 936 real visits) move(x3, y2) : -14.9 (in 936 real visits) move(x2, y3) : -2 (in 46775 real visits) move(x2, y1) : -4.3981 (in 936 real visits) move(x1, y2) : -4 (in 936 real visits) Used RAM: 344292 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 0.906763s. THTS: Maximal search depth set to 44 Search time: 0.906775s Statistics of THTS: Performed trials: 50308 Created SearchNodes: 154023 Cache Hits: 21363 Skipped backups: 21635214 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 50312 real visits) Q-Value Estimates: noop() : -2 (in 48373 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -44 (in 968 real visits) move(x1, y3) : -3 (in 968 real visits) Used RAM: 344292 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 0.906751s. 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: 344292 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 0.911438s. 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: 344292 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 0.916194s. 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: 344292 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 0.921s. 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: 344292 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 0.925857s. 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: 344292 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 0.930761s. 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: 344292 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 0.935722s. 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: 344292 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 0.940737s. 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: 344292 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 0.945805s. 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: 344292 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 0.950929s. 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: 344292 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 0.956109s. 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: 344292 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 0.961346s. 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: 344292 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 0.966641s. 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: 344292 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 0.971994s. 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: 344292 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 0.977408s. 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: 344292 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 0.982876s. 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: 344292 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 0.988412s. 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: 344292 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 0.994011s. 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: 344292 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 0.999674s. 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: 344292 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 1.0054s. 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: 344292 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 1.0112s. 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: 344292 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 1.01706s. 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: 344292 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 1.02299s. 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: 344292 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 1.02899s. 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: 344292 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 1.03506s. 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: 344292 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 1.0412s. 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: 344292 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 1.04742s. 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: 344292 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 1.05371s. 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: 344292 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 1.06008s. 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: 344292 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 1.06652s. 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: 344292 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 1.07305s. 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: 344292 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 1.07965s. 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: 344292 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 1.08634s. 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: 344292 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 1.09311s. 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: 344292 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 1.09996s. 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: 344292 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 1.10691s. 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: 344292 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 1.11394s. 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: 344292 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 1.12106s. 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: 344292 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 1.12827s. 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: 344292 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 1.13558s. 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: 344292 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 1.14298s. 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: 344292 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 1.15048s. 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: 344292 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 1.15808s. 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: 225812 Accumulated number of search nodes in root state: 715966 Used RAM: 344292 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 1.16578s. THTS: Maximal search depth set to 50 Search time: 1.16581s Statistics of THTS: Performed trials: 62454 Created SearchNodes: 195825 Cache Hits: 25350 Action Selection: Exploitation in Root: 60069 Exploration in Root: 2385 Percentage Exploration in Root: 0.0381881 Skipped backups: 22927064 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42775 (in 62457 real visits) Q-Value Estimates: noop() : -5.38433 (in 1202 real visits) move(x3, y2) : -16.4 (in 1202 real visits) move(x2, y1) : -4.42775 (in 60053 real visits) Used RAM: 348244 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 1.16577s. THTS: Maximal search depth set to 49 Search time: 1.16579s Statistics of THTS: Performed trials: 61736 Created SearchNodes: 193964 Cache Hits: 24385 Skipped backups: 24189004 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42804 (in 61740 real visits) Q-Value Estimates: noop() : -4.42804 (in 58245 real visits) move(x3, y1) : -5.3819 (in 1165 real visits) move(x2, y2) : -49 (in 1165 real visits) move(x1, y1) : -5.3711 (in 1165 real visits) Used RAM: 348508 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 1.16575s. THTS: Maximal search depth set to 48 Search time: 1.16577s Statistics of THTS: Performed trials: 63913 Created SearchNodes: 198615 Cache Hits: 26903 Skipped backups: 25521040 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 63917 real visits) Q-Value Estimates: noop() : -4.4089 (in 1206 real visits) move(x3, y1) : -5.39567 (in 1206 real visits) move(x2, y2) : -3 (in 60299 real visits) move(x1, y1) : -5 (in 1206 real visits) Used RAM: 348508 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 1.16574s. THTS: Maximal search depth set to 47 Search time: 1.16577s Statistics of THTS: Performed trials: 64441 Created SearchNodes: 199036 Cache Hits: 27548 Skipped backups: 26887732 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 64446 real visits) Q-Value Estimates: noop() : -3 (in 1194 real visits) move(x3, y2) : -15.5 (in 1194 real visits) move(x2, y3) : -2 (in 59670 real visits) move(x2, y1) : -4.417 (in 1194 real visits) move(x1, y2) : -4 (in 1194 real visits) Used RAM: 348508 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 1.16573s. THTS: Maximal search depth set to 46 Search time: 1.16573s Statistics of THTS: Performed trials: 64485 Created SearchNodes: 199226 Cache Hits: 27781 Skipped backups: 28283170 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 64489 real visits) Q-Value Estimates: noop() : -2 (in 62004 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 1241 real visits) move(x1, y3) : -3 (in 1241 real visits) Used RAM: 348772 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 1.16571s. 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: 348772 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 1.17375s. 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: 348772 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 1.18193s. 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: 348772 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 1.19023s. 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: 348772 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 1.19865s. 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: 348772 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 1.20719s. 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: 348772 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 1.21585s. 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: 348772 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 1.22464s. 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: 348772 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 1.23355s. 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: 348772 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 1.2426s. 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: 348772 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 1.25178s. 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: 348772 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 1.2611s. 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: 348772 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 1.27055s. 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: 348772 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 1.28015s. 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: 348772 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 1.2899s. 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: 348772 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 1.29979s. 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: 348772 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 1.30984s. 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: 348772 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 1.32005s. 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: 348772 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 1.33043s. 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: 348772 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 1.34095s. 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: 348772 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 1.35166s. 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: 348772 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 1.36253s. 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: 348772 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 1.37358s. 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: 348772 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 1.38481s. 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: 348772 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 1.39623s. 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: 348772 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 1.40784s. 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: 348772 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 1.41964s. 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: 348772 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 1.43164s. 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: 348772 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 1.44385s. 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: 348772 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 1.45626s. 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: 348772 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 1.4689s. 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: 348772 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 1.48175s. 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: 348772 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 1.49484s. 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: 348772 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 1.50815s. 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: 348772 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 1.52171s. 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: 348772 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 1.53552s. 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: 348772 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 1.54957s. 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: 348772 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 1.56389s. 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: 348772 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 1.57848s. 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: 348772 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 1.59334s. 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: 348772 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 1.60848s. 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: 348772 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 1.62391s. 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: 348772 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 1.63964s. 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: 348772 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 1.65569s. 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: 348772 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 1.67205s. 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: 288266 Accumulated number of search nodes in root state: 911791 Used RAM: 348772 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 1.68873s. THTS: Maximal search depth set to 50 Search time: 1.68876s Statistics of THTS: Performed trials: 88978 Created SearchNodes: 278600 Cache Hits: 36155 Action Selection: Exploitation in Root: 85577 Exploration in Root: 3401 Percentage Exploration in Root: 0.0382229 Skipped backups: 30204788 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42804 (in 88981 real visits) Q-Value Estimates: noop() : -5.3819 (in 1712 real visits) move(x3, y2) : -16.4 (in 1712 real visits) move(x2, y1) : -4.42804 (in 85557 real visits) Used RAM: 356956 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 1.68871s. THTS: Maximal search depth set to 49 Search time: 1.68872s Statistics of THTS: Performed trials: 90132 Created SearchNodes: 279687 Cache Hits: 37932 Skipped backups: 32161282 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 90136 real visits) Q-Value Estimates: noop() : -4.4089 (in 1701 real visits) move(x3, y1) : -5.38757 (in 1701 real visits) move(x2, y2) : -3 (in 85033 real visits) move(x1, y1) : -5 (in 1701 real visits) Used RAM: 356956 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 1.68869s. THTS: Maximal search depth set to 48 Search time: 1.68871s Statistics of THTS: Performed trials: 89442 Created SearchNodes: 273747 Cache Hits: 37482 Skipped backups: 34138710 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 89447 real visits) Q-Value Estimates: noop() : -48 (in 1657 real visits) move(x3, y2) : -15.8 (in 1657 real visits) move(x2, y3) : -2 (in 82819 real visits) move(x2, y1) : -4.417 (in 1657 real visits) move(x1, y2) : -4 (in 1657 real visits) Used RAM: 356956 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 1.68867s. THTS: Maximal search depth set to 47 Search time: 1.68868s Statistics of THTS: Performed trials: 88863 Created SearchNodes: 274100 Cache Hits: 38225 Skipped backups: 36135366 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 88867 real visits) Q-Value Estimates: noop() : -2 (in 85446 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -3 (in 1709 real visits) move(x1, y3) : -3 (in 1709 real visits) Used RAM: 356956 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 1.68865s. 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: 356956 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 1.70629s. 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: 356956 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 1.72441s. 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: 356956 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 1.74291s. 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: 356956 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 1.76182s. 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: 356956 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 1.78113s. 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: 356956 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 1.80088s. 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: 356956 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 1.82108s. 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: 356956 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 1.84173s. 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: 356956 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 1.86285s. 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: 356956 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 1.88447s. 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: 356956 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 1.90659s. 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: 356956 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 1.92925s. 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: 356956 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 1.95245s. 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: 356956 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 1.97621s. 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: 356956 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 2.00056s. 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: 356956 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 2.02553s. 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: 356956 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 2.05111s. 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: 356956 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 2.07736s. 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: 356956 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 2.10429s. 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: 356956 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 2.13192s. 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: 356956 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 2.16031s. 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: 356956 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 2.18945s. 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: 356956 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 2.21938s. 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: 356956 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 2.25015s. 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: 356956 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 2.2818s. 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: 356956 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 2.31434s. 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: 356956 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 2.34783s. 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: 356956 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 2.38229s. 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: 356956 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 2.41779s. 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: 356956 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 2.45438s. 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: 356956 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 2.49208s. 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: 356956 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 2.53095s. 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: 356956 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 2.57106s. 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: 356956 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 2.61248s. 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: 356956 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 2.65525s. 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: 356956 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 2.69943s. 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: 356956 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 2.74512s. 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: 356956 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 2.79238s. 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: 356956 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 2.84132s. 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: 356956 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 2.89198s. 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: 356956 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 2.94449s. 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: 356956 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 2.99894s. 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: 356956 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 3.05547s. 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: 356956 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 3.11413s. 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: 356956 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 3.17512s. 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: 377244 Accumulated number of search nodes in root state: 1190391 Used RAM: 356956 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 3.23854s. THTS: Maximal search depth set to 50 Search time: 3.23857s Statistics of THTS: Performed trials: 165323 Created SearchNodes: 514582 Cache Hits: 67653 Action Selection: Exploitation in Root: 158971 Exploration in Root: 6352 Percentage Exploration in Root: 0.0384218 Skipped backups: 39963256 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -4.42826 (in 165326 real visits) Q-Value Estimates: noop() : -5.40323 (in 3180 real visits) move(x3, y2) : -16.4 (in 3180 real visits) move(x2, y1) : -4.42826 (in 158966 real visits) Used RAM: 380980 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 3.23851s. THTS: Maximal search depth set to 49 Search time: 3.23851s Statistics of THTS: Performed trials: 167015 Created SearchNodes: 516296 Cache Hits: 70310 Skipped backups: 43852500 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -3 (in 167019 real visits) Q-Value Estimates: noop() : -4.417 (in 3152 real visits) move(x3, y1) : -5.39567 (in 3152 real visits) move(x2, y2) : -3 (in 157563 real visits) move(x1, y1) : -5 (in 3152 real visits) Used RAM: 380980 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 3.23846s. THTS: Maximal search depth set to 48 Search time: 3.23846s Statistics of THTS: Performed trials: 168130 Created SearchNodes: 517750 Cache Hits: 71329 Skipped backups: 47822136 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -2 (in 168135 real visits) Q-Value Estimates: noop() : -3 (in 3114 real visits) move(x3, y2) : -15.8 (in 3114 real visits) move(x2, y3) : -2 (in 155679 real visits) move(x2, y1) : -4.3981 (in 3114 real visits) move(x1, y2) : -4 (in 3114 real visits) Used RAM: 381244 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 3.23843s. THTS: Maximal search depth set to 47 Search time: 3.23845s Statistics of THTS: Performed trials: 166239 Created SearchNodes: 507897 Cache Hits: 69865 Skipped backups: 51839620 Initializer: ExpandNode Heuristic weight: 1 Number of initial visits: 1 Heuristic: Statistics of DD Heuristic Seach[Steps: 50]: Root Node: -1 (in 166243 real visits) Q-Value Estimates: noop() : -2 (in 159846 real visits) move(x3, y3) : SOLVED with: -1 (in 3 real visits) move(x2, y2) : -47 (in 3197 real visits) move(x1, y3) : -3 (in 3197 real visits) Used RAM: 381244 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 3.23837s. 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: 381244 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 3.30984s. 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: 381244 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 3.38495s. 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: 381244 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 3.46356s. 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: 381244 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 3.54588s. 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: 381244 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 3.63224s. 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: 381244 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 3.72293s. 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: 381244 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 3.81823s. 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: 381244 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 3.91858s. 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: 381244 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 4.02435s. 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: 381244 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 4.136s. 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: 381244 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 4.254s. 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: 381244 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 4.37897s. 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: 381244 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 4.51152s. 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: 381244 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 4.65234s. 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: 381244 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 4.80223s. 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: 381244 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 4.96213s. 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: 381244 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 5.13307s. 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: 381244 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 5.31618s. 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: 381244 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 5.51289s. 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: 381244 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 5.72473s. 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: 381244 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 5.95348s. 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: 381244 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 6.20133s. 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: 381244 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 6.47074s. 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: 381244 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 6.76464s. 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: 381244 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 7.08648s. 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: 381244 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 7.44055s. 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: 381244 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 7.83184s. 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: 381244 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 8.26667s. 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: 381244 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 8.75265s. 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: 381244 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 9.29931s. 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: 381244 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 9.91893s. 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: 381244 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 10.6271s. 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: 381244 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 11.4441s. 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: 381244 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 12.3973s. 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: 381244 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 13.5239s. 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: 381244 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 14.8758s. 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: 381244 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 16.528s. 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: 381244 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 18.5934s. 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: 381244 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 21.2489s. 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: 381244 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 24.7895s. 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: 381244 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 29.7462s. 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: 381244 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 37.1815s. 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: 381244 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 49.5737s. 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: 381244 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 74.3575s. 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: 381244 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 148.71s. 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: 542567 Accumulated number of search nodes in root state: 1704973 Used RAM: 381244 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: 92.3028s