├── .gitignore ├── README.md ├── chapter1_basic ├── gridworld.py ├── gym_play.py ├── q_learning.py └── sarsa.py ├── chapter2_dqn ├── s1_dqn_begin │ ├── agents.py │ ├── modules.py │ └── train.py ├── s2_dqn_reply_buffer │ ├── agents.py │ ├── modules.py │ ├── replay_buffers.py │ └── train.py ├── s3_dqn_fix_Q_target │ ├── agents.py │ ├── modules.py │ ├── replay_buffers.py │ └── train.py ├── s4_dqn_epsilon_decay │ ├── agents.py │ ├── explorers.py │ ├── modules.py │ ├── replay_buffers.py │ └── train.py └── s5_dqn_pfrl │ ├── modules.py │ ├── train.py │ └── train_super_simple.py ├── pdfs └── 强化学习入门.pdf ├── requirements.txt └── utils └── torchUtils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # reinforcement_torch_pfrl 2 | 真-极简强化学习(代码基于torch) 3 | 4 | 注意GYM版本最好使用0.18.0。 -------------------------------------------------------------------------------- /chapter1_basic/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter1_basic/gridworld.py -------------------------------------------------------------------------------- /chapter1_basic/gym_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter1_basic/gym_play.py -------------------------------------------------------------------------------- /chapter1_basic/q_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter1_basic/q_learning.py -------------------------------------------------------------------------------- /chapter1_basic/sarsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter1_basic/sarsa.py -------------------------------------------------------------------------------- /chapter2_dqn/s1_dqn_begin/agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s1_dqn_begin/agents.py -------------------------------------------------------------------------------- /chapter2_dqn/s1_dqn_begin/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s1_dqn_begin/modules.py -------------------------------------------------------------------------------- /chapter2_dqn/s1_dqn_begin/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s1_dqn_begin/train.py -------------------------------------------------------------------------------- /chapter2_dqn/s2_dqn_reply_buffer/agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s2_dqn_reply_buffer/agents.py -------------------------------------------------------------------------------- /chapter2_dqn/s2_dqn_reply_buffer/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s2_dqn_reply_buffer/modules.py -------------------------------------------------------------------------------- /chapter2_dqn/s2_dqn_reply_buffer/replay_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s2_dqn_reply_buffer/replay_buffers.py -------------------------------------------------------------------------------- /chapter2_dqn/s2_dqn_reply_buffer/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s2_dqn_reply_buffer/train.py -------------------------------------------------------------------------------- /chapter2_dqn/s3_dqn_fix_Q_target/agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s3_dqn_fix_Q_target/agents.py -------------------------------------------------------------------------------- /chapter2_dqn/s3_dqn_fix_Q_target/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s3_dqn_fix_Q_target/modules.py -------------------------------------------------------------------------------- /chapter2_dqn/s3_dqn_fix_Q_target/replay_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s3_dqn_fix_Q_target/replay_buffers.py -------------------------------------------------------------------------------- /chapter2_dqn/s3_dqn_fix_Q_target/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s3_dqn_fix_Q_target/train.py -------------------------------------------------------------------------------- /chapter2_dqn/s4_dqn_epsilon_decay/agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s4_dqn_epsilon_decay/agents.py -------------------------------------------------------------------------------- /chapter2_dqn/s4_dqn_epsilon_decay/explorers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s4_dqn_epsilon_decay/explorers.py -------------------------------------------------------------------------------- /chapter2_dqn/s4_dqn_epsilon_decay/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s4_dqn_epsilon_decay/modules.py -------------------------------------------------------------------------------- /chapter2_dqn/s4_dqn_epsilon_decay/replay_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s4_dqn_epsilon_decay/replay_buffers.py -------------------------------------------------------------------------------- /chapter2_dqn/s4_dqn_epsilon_decay/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s4_dqn_epsilon_decay/train.py -------------------------------------------------------------------------------- /chapter2_dqn/s5_dqn_pfrl/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s5_dqn_pfrl/modules.py -------------------------------------------------------------------------------- /chapter2_dqn/s5_dqn_pfrl/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s5_dqn_pfrl/train.py -------------------------------------------------------------------------------- /chapter2_dqn/s5_dqn_pfrl/train_super_simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/chapter2_dqn/s5_dqn_pfrl/train_super_simple.py -------------------------------------------------------------------------------- /pdfs/强化学习入门.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/pdfs/强化学习入门.pdf -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/requirements.txt -------------------------------------------------------------------------------- /utils/torchUtils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rexrex9/reinforcement_torch_pfrl/HEAD/utils/torchUtils.py --------------------------------------------------------------------------------