[{"title":"( 15 个子文件 63KB ) rl-ml-master_Qlearning_Q-learning_rockzcb_www.559Rl.com_world","children":[{"title":"rl-ml-master","children":[{"title":"source","children":[{"title":"epsilonGreedy.m <span style='color:#111;'> 802B </span>","children":null,"spread":false},{"title":"QLearnTrial.m <span style='color:#111;'> 713B </span>","children":null,"spread":false},{"title":"plot_grid.m <span style='color:#111;'> 860B </span>","children":null,"spread":false},{"title":"task1.mat <span style='color:#111;'> 586B </span>","children":null,"spread":false},{"title":"Task1.m <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"RL_main.m <span style='color:#111;'> 559B </span>","children":null,"spread":false},{"title":"QLearnTrials.m <span style='color:#111;'> 835B </span>","children":null,"spread":false},{"title":"walkOptimalPolicy.m <span style='color:#111;'> 490B </span>","children":null,"spread":false},{"title":"decay.m <span style='color:#111;'> 468B </span>","children":null,"spread":false},{"title":"transition.m <span style='color:#111;'> 576B </span>","children":null,"spread":false},{"title":"calculateOptimalPolicy.m <span style='color:#111;'> 154B </span>","children":null,"spread":false}],"spread":false},{"title":"images","children":[{"title":"Figure2.png <span style='color:#111;'> 9.05KB </span>","children":null,"spread":false},{"title":"Figure1.png <span style='color:#111;'> 38.20KB </span>","children":null,"spread":false},{"title":"Figure3.png <span style='color:#111;'> 14.58KB </span>","children":null,"spread":false}],"spread":true},{"title":"readme.md <span style='color:#111;'> 4.68KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]