├── .gitignore ├── README.md ├── figures ├── 01_dqn.png ├── 02_ddpg.png ├── 03_a2c.png ├── 04_trpo.png ├── 05_ppo.png ├── 06_sac.png ├── bipedal.gif ├── breakout.gif ├── hopper.gif └── logo.png ├── rl_algorithms ├── a2c │ ├── README.md │ ├── a2c_agent.py │ ├── arguments.py │ ├── demo.py │ ├── models.py │ ├── train.py │ └── utils.py ├── ddpg │ ├── README.md │ ├── arguments.py │ ├── ddpg_agent.py │ ├── demo.py │ ├── models.py │ ├── train.py │ └── utils.py ├── dqn_algos │ ├── README.md │ ├── arguments.py │ ├── demo.py │ ├── dqn_agent.py │ ├── models.py │ ├── train.py │ └── utils.py ├── ppo │ ├── README.md │ ├── arguments.py │ ├── demo.py │ ├── models.py │ ├── ppo_agent.py │ ├── train.py │ └── utils.py ├── sac │ ├── README.md │ ├── arguments.py │ ├── demo.py │ ├── models.py │ ├── sac_agent.py │ ├── train.py │ └── utils.py └── trpo │ ├── README.md │ ├── arguments.py │ ├── demo.py │ ├── models.py │ ├── train.py │ ├── trpo_agent.py │ └── utils.py ├── rl_utils ├── __init__.py ├── env_wrapper │ ├── __init__.py │ ├── atari_wrapper.py │ ├── create_env.py │ ├── frame_stack.py │ └── multi_envs_wrapper.py ├── experience_replay │ └── experience_replay.py ├── logger │ ├── __init__.py │ ├── bench.py │ ├── logger.py │ └── plot.py ├── mpi_utils │ ├── __init__.py │ ├── normalizer.py │ └── utils.py ├── running_filter │ ├── __init__.py │ └── running_filter.py └── seeds │ └── seeds.py └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/README.md -------------------------------------------------------------------------------- /figures/01_dqn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/01_dqn.png -------------------------------------------------------------------------------- /figures/02_ddpg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/02_ddpg.png -------------------------------------------------------------------------------- /figures/03_a2c.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/03_a2c.png -------------------------------------------------------------------------------- /figures/04_trpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/04_trpo.png -------------------------------------------------------------------------------- /figures/05_ppo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/05_ppo.png -------------------------------------------------------------------------------- /figures/06_sac.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/06_sac.png -------------------------------------------------------------------------------- /figures/bipedal.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/bipedal.gif -------------------------------------------------------------------------------- /figures/breakout.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/breakout.gif -------------------------------------------------------------------------------- /figures/hopper.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/hopper.gif -------------------------------------------------------------------------------- /figures/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/figures/logo.png -------------------------------------------------------------------------------- /rl_algorithms/a2c/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/README.md -------------------------------------------------------------------------------- /rl_algorithms/a2c/a2c_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/a2c_agent.py -------------------------------------------------------------------------------- /rl_algorithms/a2c/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/arguments.py -------------------------------------------------------------------------------- /rl_algorithms/a2c/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/demo.py -------------------------------------------------------------------------------- /rl_algorithms/a2c/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/models.py -------------------------------------------------------------------------------- /rl_algorithms/a2c/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/train.py -------------------------------------------------------------------------------- /rl_algorithms/a2c/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/a2c/utils.py -------------------------------------------------------------------------------- /rl_algorithms/ddpg/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/README.md -------------------------------------------------------------------------------- /rl_algorithms/ddpg/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/arguments.py -------------------------------------------------------------------------------- /rl_algorithms/ddpg/ddpg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/ddpg_agent.py -------------------------------------------------------------------------------- /rl_algorithms/ddpg/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/demo.py -------------------------------------------------------------------------------- /rl_algorithms/ddpg/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/models.py -------------------------------------------------------------------------------- /rl_algorithms/ddpg/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/train.py -------------------------------------------------------------------------------- /rl_algorithms/ddpg/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ddpg/utils.py -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/README.md -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/arguments.py -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/demo.py -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/dqn_agent.py -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/models.py -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/train.py -------------------------------------------------------------------------------- /rl_algorithms/dqn_algos/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/dqn_algos/utils.py -------------------------------------------------------------------------------- /rl_algorithms/ppo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/README.md -------------------------------------------------------------------------------- /rl_algorithms/ppo/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/arguments.py -------------------------------------------------------------------------------- /rl_algorithms/ppo/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/demo.py -------------------------------------------------------------------------------- /rl_algorithms/ppo/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/models.py -------------------------------------------------------------------------------- /rl_algorithms/ppo/ppo_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/ppo_agent.py -------------------------------------------------------------------------------- /rl_algorithms/ppo/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/train.py -------------------------------------------------------------------------------- /rl_algorithms/ppo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/ppo/utils.py -------------------------------------------------------------------------------- /rl_algorithms/sac/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/README.md -------------------------------------------------------------------------------- /rl_algorithms/sac/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/arguments.py -------------------------------------------------------------------------------- /rl_algorithms/sac/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/demo.py -------------------------------------------------------------------------------- /rl_algorithms/sac/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/models.py -------------------------------------------------------------------------------- /rl_algorithms/sac/sac_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/sac_agent.py -------------------------------------------------------------------------------- /rl_algorithms/sac/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/train.py -------------------------------------------------------------------------------- /rl_algorithms/sac/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/sac/utils.py -------------------------------------------------------------------------------- /rl_algorithms/trpo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/README.md -------------------------------------------------------------------------------- /rl_algorithms/trpo/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/arguments.py -------------------------------------------------------------------------------- /rl_algorithms/trpo/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/demo.py -------------------------------------------------------------------------------- /rl_algorithms/trpo/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/models.py -------------------------------------------------------------------------------- /rl_algorithms/trpo/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/train.py -------------------------------------------------------------------------------- /rl_algorithms/trpo/trpo_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/trpo_agent.py -------------------------------------------------------------------------------- /rl_algorithms/trpo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_algorithms/trpo/utils.py -------------------------------------------------------------------------------- /rl_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_utils/env_wrapper/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/env_wrapper/__init__.py -------------------------------------------------------------------------------- /rl_utils/env_wrapper/atari_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/env_wrapper/atari_wrapper.py -------------------------------------------------------------------------------- /rl_utils/env_wrapper/create_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/env_wrapper/create_env.py -------------------------------------------------------------------------------- /rl_utils/env_wrapper/frame_stack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/env_wrapper/frame_stack.py -------------------------------------------------------------------------------- /rl_utils/env_wrapper/multi_envs_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/env_wrapper/multi_envs_wrapper.py -------------------------------------------------------------------------------- /rl_utils/experience_replay/experience_replay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/experience_replay/experience_replay.py -------------------------------------------------------------------------------- /rl_utils/logger/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_utils/logger/bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/logger/bench.py -------------------------------------------------------------------------------- /rl_utils/logger/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/logger/logger.py -------------------------------------------------------------------------------- /rl_utils/logger/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/logger/plot.py -------------------------------------------------------------------------------- /rl_utils/mpi_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_utils/mpi_utils/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/mpi_utils/normalizer.py -------------------------------------------------------------------------------- /rl_utils/mpi_utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/mpi_utils/utils.py -------------------------------------------------------------------------------- /rl_utils/running_filter/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_utils/running_filter/running_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/running_filter/running_filter.py -------------------------------------------------------------------------------- /rl_utils/seeds/seeds.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/rl_utils/seeds/seeds.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TianhongDai/reinforcement-learning-algorithms/HEAD/setup.py --------------------------------------------------------------------------------