reinforcement-learning-an-introduction-master.rar

[{"title":"（ 43 个子文件 537KB ） reinforcement-learning-an-introduction-master.rar","children":[{"title":"reinforcement-learning-an-introduction-master","children":[{"title":".gitignore <span style='color:#111;'> 49B </span>","children":null,"spread":false},{"title":"chapter08","children":[{"title":"expectation_vs_sample.py <span style='color:#111;'> 1.59KB </span>","children":null,"spread":false},{"title":"trajectory_sampling.py <span style='color:#111;'> 4.80KB </span>","children":null,"spread":false},{"title":"maze.py <span style='color:#111;'> 22.68KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 10.25KB </span>","children":null,"spread":false},{"title":"chapter05","children":[{"title":"infinite_variance.py <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"blackjack.py <span style='color:#111;'> 13.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"chapter12","children":[{"title":"mountain_car.py <span style='color:#111;'> 11.86KB </span>","children":null,"spread":false},{"title":"lambda_effect.py <span style='color:#111;'> 45.47KB </span>","children":null,"spread":false},{"title":"random_walk.py <span style='color:#111;'> 9.41KB </span>","children":null,"spread":false}],"spread":true},{"title":"chapter01","children":[{"title":"tic_tac_toe.py <span style='color:#111;'> 10.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"chapter11","children":[{"title":"counterexample.py <span style='color:#111;'> 11.56KB </span>","children":null,"spread":false}],"spread":true},{"title":"chapter03","children":[{"title":"grid_world.py <span style='color:#111;'> 6.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"chapter06","children":[{"title":"cliff_walking.py <span style='color:#111;'> 9.14KB </span>","children":null,"spread":false},{"title":"maximization_bias.py <span style='color:#111;'> 4.17KB </span>","children":null,"spread":false},{"title":"windy_grid_world.py <span style='color:#111;'> 3.92KB </span>","children":null,"spread":false},{"title":"random_walk.py <span style='color:#111;'> 6.42KB </span>","children":null,"spread":false}],"spread":true},{"title":"chapter09","children":[{"title":"square_wave.py <span style='color:#111;'> 4.16KB </span>","children":null,"spread":false},{"title":"random_walk.py <span style='color:#111;'> 15.57KB </span>","children":null,"spread":false}],"spread":true},{"title":".idea","children":[{"title":".gitignore <span style='color:#111;'> 50B </span>","children":null,"spread":false},{"title":"workspace.xml <span style='color:#111;'> 5.79KB </span>","children":null,"spread":false},{"title":"misc.xml <span style='color:#111;'> 188B </span>","children":null,"spread":false},{"title":"modules.xml <span style='color:#111;'> 349B </span>","children":null,"spread":false},{"title":"inspectionProfiles","children":[{"title":"profiles_settings.xml <span style='color:#111;'> 174B </span>","children":null,"spread":false}],"spread":false},{"title":"reinforcement-learning-an-introduction-master.iml <span style='color:#111;'> 566B </span>","children":null,"spread":false}],"spread":true},{"title":"images","children":[{"title":"figure_13_2.png <span style='color:#111;'> 39.96KB </span>","children":null,"spread":false},{"title":"figure_12_11.png <span style='color:#111;'> 44.95KB </span>","children":null,"spread":false},{"title":"example_13_1.png <span style='color:#111;'> 35.05KB </span>","children":null,"spread":false},{"title":"example_6_2.png <span style='color:#111;'> 232.55KB </span>","children":null,"spread":false},{"title":"figure_13_1.png <span style='color:#111;'> 58.88KB </span>","children":null,"spread":false},{"title":"figure_12_10.png <span style='color:#111;'> 47.77KB </span>","children":null,"spread":false},{"title":"example_8_4.png <span style='color:#111;'> 30.75KB </span>","children":null,"spread":false}],"spread":true},{"title":"chapter02","children":[{"title":"ten_armed_testbed.py <span style='color:#111;'> 8.89KB </span>","children":null,"spread":false}],"spread":false},{"title":".travis.yml <span style='color:#111;'> 148B </span>","children":null,"spread":false},{"title":"chapter13","children":[{"title":"short_corridor.py <span style='color:#111;'> 8.20KB </span>","children":null,"spread":false}],"spread":false},{"title":"chapter07","children":[{"title":"random_walk.py <span style='color:#111;'> 4.12KB </span>","children":null,"spread":false}],"spread":false},{"title":"chapter10","children":[{"title":"mountain_car.py <span style='color:#111;'> 13.36KB </span>","children":null,"spread":false},{"title":"access_control.py <span style='color:#111;'> 9.38KB </span>","children":null,"spread":false}],"spread":false},{"title":"chapter04","children":[{"title":"car_rental.py <span style='color:#111;'> 7.47KB </span>","children":null,"spread":false},{"title":"car_rental_synchronous.py <span style='color:#111;'> 8.54KB </span>","children":null,"spread":false},{"title":"gamblers_problem.py <span style='color:#111;'> 2.61KB </span>","children":null,"spread":false},{"title":"grid_world.py <span style='color:#111;'> 3.25KB </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true}]