├── README.md └── content ├── 1_treasure_on_right └── treasure_on_right.py ├── 2_Q-learning-maze ├── RL_brain.py ├── maze_env.py └── run_this.py ├── 3_Sarsa_maze ├── RL_brain.py ├── maze_env.py └── run_this.py ├── 4_Sarsa_lambda_maze ├── RL_brain.py ├── maze_env.py └── run_this.py ├── 5.1_double_DQN ├── RL_brain.py └── run_Pendulum.py ├── 5.2_Prioritized_Replay_DQN ├── Figure_1.png ├── RL_brain.py └── run_MountainCar.py ├── 5.3_Dueling_DQN ├── RL_brain.py ├── action15.png └── run_Pendulum.py ├── 5_Deep_Q_Network ├── RL_brain.py ├── maze_env.py └── run_this.py ├── 7_Policy_gradient_softmax ├── RL_brain.py ├── run_CartPole.py └── run_MountainCar.py └── 8_Actor_Critic_Advantage ├── AC_CartPole.py └── AC_continue_Pendulum.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/README.md -------------------------------------------------------------------------------- /content/1_treasure_on_right/treasure_on_right.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/1_treasure_on_right/treasure_on_right.py -------------------------------------------------------------------------------- /content/2_Q-learning-maze/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/2_Q-learning-maze/RL_brain.py -------------------------------------------------------------------------------- /content/2_Q-learning-maze/maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/2_Q-learning-maze/maze_env.py -------------------------------------------------------------------------------- /content/2_Q-learning-maze/run_this.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/2_Q-learning-maze/run_this.py -------------------------------------------------------------------------------- /content/3_Sarsa_maze/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/3_Sarsa_maze/RL_brain.py -------------------------------------------------------------------------------- /content/3_Sarsa_maze/maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/3_Sarsa_maze/maze_env.py -------------------------------------------------------------------------------- /content/3_Sarsa_maze/run_this.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/3_Sarsa_maze/run_this.py -------------------------------------------------------------------------------- /content/4_Sarsa_lambda_maze/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/4_Sarsa_lambda_maze/RL_brain.py -------------------------------------------------------------------------------- /content/4_Sarsa_lambda_maze/maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/4_Sarsa_lambda_maze/maze_env.py -------------------------------------------------------------------------------- /content/4_Sarsa_lambda_maze/run_this.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/4_Sarsa_lambda_maze/run_this.py -------------------------------------------------------------------------------- /content/5.1_double_DQN/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.1_double_DQN/RL_brain.py -------------------------------------------------------------------------------- /content/5.1_double_DQN/run_Pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.1_double_DQN/run_Pendulum.py -------------------------------------------------------------------------------- /content/5.2_Prioritized_Replay_DQN/Figure_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.2_Prioritized_Replay_DQN/Figure_1.png -------------------------------------------------------------------------------- /content/5.2_Prioritized_Replay_DQN/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.2_Prioritized_Replay_DQN/RL_brain.py -------------------------------------------------------------------------------- /content/5.2_Prioritized_Replay_DQN/run_MountainCar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.2_Prioritized_Replay_DQN/run_MountainCar.py -------------------------------------------------------------------------------- /content/5.3_Dueling_DQN/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.3_Dueling_DQN/RL_brain.py -------------------------------------------------------------------------------- /content/5.3_Dueling_DQN/action15.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.3_Dueling_DQN/action15.png -------------------------------------------------------------------------------- /content/5.3_Dueling_DQN/run_Pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5.3_Dueling_DQN/run_Pendulum.py -------------------------------------------------------------------------------- /content/5_Deep_Q_Network/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5_Deep_Q_Network/RL_brain.py -------------------------------------------------------------------------------- /content/5_Deep_Q_Network/maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5_Deep_Q_Network/maze_env.py -------------------------------------------------------------------------------- /content/5_Deep_Q_Network/run_this.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/5_Deep_Q_Network/run_this.py -------------------------------------------------------------------------------- /content/7_Policy_gradient_softmax/RL_brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/7_Policy_gradient_softmax/RL_brain.py -------------------------------------------------------------------------------- /content/7_Policy_gradient_softmax/run_CartPole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/7_Policy_gradient_softmax/run_CartPole.py -------------------------------------------------------------------------------- /content/7_Policy_gradient_softmax/run_MountainCar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/7_Policy_gradient_softmax/run_MountainCar.py -------------------------------------------------------------------------------- /content/8_Actor_Critic_Advantage/AC_CartPole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/8_Actor_Critic_Advantage/AC_CartPole.py -------------------------------------------------------------------------------- /content/8_Actor_Critic_Advantage/AC_continue_Pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ClownW/Reinforcement-learning-with-PyTorch/HEAD/content/8_Actor_Critic_Advantage/AC_continue_Pendulum.py --------------------------------------------------------------------------------