莫烦大大的增强学习的代码实例

[{"title":"（ 52 个子文件 259KB ） 莫烦大大的增强学习的代码实例","children":[{"title":"Reinforcement-learning-with-tensorflow-master","children":[{"title":"experiments","children":[{"title":"Robot_arm","children":[{"title":"arm_env.py <span style='color:#111;'> 8.28KB </span>","children":null,"spread":false},{"title":"A3C.py <span style='color:#111;'> 8.42KB </span>","children":null,"spread":false},{"title":"DDPG.py <span style='color:#111;'> 10.13KB </span>","children":null,"spread":false}],"spread":true},{"title":"2D_car","children":[{"title":"DDPG.py <span style='color:#111;'> 9.57KB </span>","children":null,"spread":false},{"title":"collision.py <span style='color:#111;'> 2.02KB </span>","children":null,"spread":false},{"title":"car_env.py <span style='color:#111;'> 7.77KB </span>","children":null,"spread":false}],"spread":true},{"title":"Solve_BipedalWalker","children":[{"title":"A3C.py <span style='color:#111;'> 8.25KB </span>","children":null,"spread":false},{"title":"DDPG.py <span style='color:#111;'> 15.72KB </span>","children":null,"spread":false},{"title":"log","children":[{"title":"events.out.tfevents.1490801027.Morvan <span style='color:#111;'> 1.07MB </span>","children":null,"spread":false}],"spread":true},{"title":"A3C_rnn.py <span style='color:#111;'> 9.71KB </span>","children":null,"spread":false}],"spread":true},{"title":"Solve_LunarLander","children":[{"title":"A3C.py <span style='color:#111;'> 9.43KB </span>","children":null,"spread":false},{"title":"run_LunarLander.py <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false},{"title":"DuelingDQNPrioritizedReplay.py <span style='color:#111;'> 12.72KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENCE <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.61KB </span>","children":null,"spread":false},{"title":"contents","children":[{"title":"9_Deep_Deterministic_Policy_Gradient_DDPG","children":[{"title":"DDPG.py <span style='color:#111;'> 9.47KB </span>","children":null,"spread":false},{"title":"DDPG_update.py <span style='color:#111;'> 5.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"11_Dyna_Q","children":[{"title":"maze_env.py <span style='color:#111;'> 3.81KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 2.85KB </span>","children":null,"spread":false},{"title":"run_this.py <span style='color:#111;'> 1.46KB </span>","children":null,"spread":false}],"spread":true},{"title":"5.1_Double_DQN","children":[{"title":"run_Pendulum.py <span style='color:#111;'> 2.08KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 6.54KB </span>","children":null,"spread":false}],"spread":true},{"title":"6_OpenAI_gym","children":[{"title":"run_CartPole.py <span style='color:#111;'> 1.44KB </span>","children":null,"spread":false},{"title":"run_MountainCar.py <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 8.24KB </span>","children":null,"spread":false}],"spread":true},{"title":"3_Sarsa_maze","children":[{"title":"maze_env.py <span style='color:#111;'> 3.88KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 2.61KB </span>","children":null,"spread":false},{"title":"run_this.py <span style='color:#111;'> 1.47KB </span>","children":null,"spread":false}],"spread":true},{"title":"8_Actor_Critic_Advantage","children":[{"title":"AC_continue_Pendulum.py <span style='color:#111;'> 6.24KB </span>","children":null,"spread":false},{"title":"AC_CartPole.py <span style='color:#111;'> 5.72KB </span>","children":null,"spread":false}],"spread":true},{"title":"7_Policy_gradient_softmax","children":[{"title":"run_CartPole.py <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"run_MountainCar.py <span style='color:#111;'> 1.98KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 4.24KB </span>","children":null,"spread":false}],"spread":true},{"title":"5.3_Dueling_DQN","children":[{"title":"run_Pendulum.py <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 6.72KB </span>","children":null,"spread":false}],"spread":true},{"title":"10_A3C","children":[{"title":"A3C_RNN.py <span style='color:#111;'> 9.46KB </span>","children":null,"spread":false},{"title":"A3C_continuous_action.py <span style='color:#111;'> 8.12KB </span>","children":null,"spread":false},{"title":"A3C_discrete_action.py <span style='color:#111;'> 7.77KB </span>","children":null,"spread":false}],"spread":true},{"title":"2_Q_Learning_maze","children":[{"title":"maze_env.py <span style='color:#111;'> 4.17KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"run_this.py <span style='color:#111;'> 1.36KB </span>","children":null,"spread":false}],"spread":false},{"title":"5_Deep_Q_Network","children":[{"title":"DQN_modified.py <span style='color:#111;'> 6.92KB </span>","children":null,"spread":false},{"title":"maze_env.py <span style='color:#111;'> 4.07KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 8.24KB </span>","children":null,"spread":false},{"title":"run_this.py <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false}],"spread":false},{"title":"5.2_Prioritized_Replay_DQN","children":[{"title":"run_MountainCar.py <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 12.03KB </span>","children":null,"spread":false}],"spread":false},{"title":"4_Sarsa_lambda_maze","children":[{"title":"maze_env.py <span style='color:#111;'> 3.88KB </span>","children":null,"spread":false},{"title":"RL_brain.py <span style='color:#111;'> 3.06KB </span>","children":null,"spread":false},{"title":"run_this.py <span style='color:#111;'> 1.56KB </span>","children":null,"spread":false}],"spread":false},{"title":"1_command_line_reinforcement_learning","children":[{"title":"treasure_on_right.py <span style='color:#111;'> 3.27KB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"RL_cover.jpg <span style='color:#111;'> 68.07KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]