├── .gitattributes ├── .gitignore ├── README.md ├── agents ├── __init__.py ├── agent.py ├── ppo.py └── random_agent.py ├── assets ├── CartPole-V1-PPO.gif ├── MountainCar-v0-PPO.gif ├── Pendulum-v0-PPO.gif └── tensorboard.png ├── curiosity ├── __init__.py ├── base.py ├── icm.py └── no_curiosity.py ├── envs ├── __init__.py ├── converters.py ├── multi_env.py ├── runner.py └── utils.py ├── models ├── __init__.py ├── datasets.py ├── mlp.py └── model.py ├── normalizers ├── __init__.py ├── no_normalizer.py ├── normalizer.py └── standard_normalizer.py ├── reporters ├── __init__.py ├── log_reporter.py ├── no_reporter.py ├── reporter.py └── tensorboard_reporter.py ├── requirements.txt ├── rewards ├── __init__.py ├── advantage.py ├── gae.py ├── gae_reward.py ├── n_step_advantage.py ├── n_step_reward.py ├── reward.py └── utils.py ├── run_cartpole.py ├── run_mountain_car.py ├── run_pendulum.py └── test ├── agents ├── test_ppo.py └── test_random_agent.py ├── curiosity ├── test_icm.py └── test_no_curiosity.py ├── envs ├── test_converters.py ├── test_multi_env.py └── test_runner.py ├── models ├── test_datasets.py └── test_mlp.py ├── normalizers ├── test_no_normalizer.py └── test_standard_normalizer.py ├── reporters ├── test_log_reporter.py ├── test_reporter.py └── test_tensorboard_reporter.py └── rewards ├── test_gae.py ├── test_gae_reward.py ├── test_n_step_advantage.py ├── test_n_step_reward.py └── test_utils.py /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/README.md -------------------------------------------------------------------------------- /agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/agents/__init__.py -------------------------------------------------------------------------------- /agents/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/agents/agent.py -------------------------------------------------------------------------------- /agents/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/agents/ppo.py -------------------------------------------------------------------------------- /agents/random_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/agents/random_agent.py -------------------------------------------------------------------------------- /assets/CartPole-V1-PPO.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/assets/CartPole-V1-PPO.gif -------------------------------------------------------------------------------- /assets/MountainCar-v0-PPO.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/assets/MountainCar-v0-PPO.gif -------------------------------------------------------------------------------- /assets/Pendulum-v0-PPO.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/assets/Pendulum-v0-PPO.gif -------------------------------------------------------------------------------- /assets/tensorboard.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/assets/tensorboard.png -------------------------------------------------------------------------------- /curiosity/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/curiosity/__init__.py -------------------------------------------------------------------------------- /curiosity/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/curiosity/base.py -------------------------------------------------------------------------------- /curiosity/icm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/curiosity/icm.py -------------------------------------------------------------------------------- /curiosity/no_curiosity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/curiosity/no_curiosity.py -------------------------------------------------------------------------------- /envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/envs/__init__.py -------------------------------------------------------------------------------- /envs/converters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/envs/converters.py -------------------------------------------------------------------------------- /envs/multi_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/envs/multi_env.py -------------------------------------------------------------------------------- /envs/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/envs/runner.py -------------------------------------------------------------------------------- /envs/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/envs/utils.py -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/models/__init__.py -------------------------------------------------------------------------------- /models/datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/models/datasets.py -------------------------------------------------------------------------------- /models/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/models/mlp.py -------------------------------------------------------------------------------- /models/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/models/model.py -------------------------------------------------------------------------------- /normalizers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/normalizers/__init__.py -------------------------------------------------------------------------------- /normalizers/no_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/normalizers/no_normalizer.py -------------------------------------------------------------------------------- /normalizers/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/normalizers/normalizer.py -------------------------------------------------------------------------------- /normalizers/standard_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/normalizers/standard_normalizer.py -------------------------------------------------------------------------------- /reporters/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/reporters/__init__.py -------------------------------------------------------------------------------- /reporters/log_reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/reporters/log_reporter.py -------------------------------------------------------------------------------- /reporters/no_reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/reporters/no_reporter.py -------------------------------------------------------------------------------- /reporters/reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/reporters/reporter.py -------------------------------------------------------------------------------- /reporters/tensorboard_reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/reporters/tensorboard_reporter.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/requirements.txt -------------------------------------------------------------------------------- /rewards/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/__init__.py -------------------------------------------------------------------------------- /rewards/advantage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/advantage.py -------------------------------------------------------------------------------- /rewards/gae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/gae.py -------------------------------------------------------------------------------- /rewards/gae_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/gae_reward.py -------------------------------------------------------------------------------- /rewards/n_step_advantage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/n_step_advantage.py -------------------------------------------------------------------------------- /rewards/n_step_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/n_step_reward.py -------------------------------------------------------------------------------- /rewards/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/reward.py -------------------------------------------------------------------------------- /rewards/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/rewards/utils.py -------------------------------------------------------------------------------- /run_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/run_cartpole.py -------------------------------------------------------------------------------- /run_mountain_car.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/run_mountain_car.py -------------------------------------------------------------------------------- /run_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/run_pendulum.py -------------------------------------------------------------------------------- /test/agents/test_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/agents/test_ppo.py -------------------------------------------------------------------------------- /test/agents/test_random_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/agents/test_random_agent.py -------------------------------------------------------------------------------- /test/curiosity/test_icm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/curiosity/test_icm.py -------------------------------------------------------------------------------- /test/curiosity/test_no_curiosity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/curiosity/test_no_curiosity.py -------------------------------------------------------------------------------- /test/envs/test_converters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/envs/test_converters.py -------------------------------------------------------------------------------- /test/envs/test_multi_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/envs/test_multi_env.py -------------------------------------------------------------------------------- /test/envs/test_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/envs/test_runner.py -------------------------------------------------------------------------------- /test/models/test_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/models/test_datasets.py -------------------------------------------------------------------------------- /test/models/test_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/models/test_mlp.py -------------------------------------------------------------------------------- /test/normalizers/test_no_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/normalizers/test_no_normalizer.py -------------------------------------------------------------------------------- /test/normalizers/test_standard_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/normalizers/test_standard_normalizer.py -------------------------------------------------------------------------------- /test/reporters/test_log_reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/reporters/test_log_reporter.py -------------------------------------------------------------------------------- /test/reporters/test_reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/reporters/test_reporter.py -------------------------------------------------------------------------------- /test/reporters/test_tensorboard_reporter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/reporters/test_tensorboard_reporter.py -------------------------------------------------------------------------------- /test/rewards/test_gae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/rewards/test_gae.py -------------------------------------------------------------------------------- /test/rewards/test_gae_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/rewards/test_gae_reward.py -------------------------------------------------------------------------------- /test/rewards/test_n_step_advantage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/rewards/test_n_step_advantage.py -------------------------------------------------------------------------------- /test/rewards/test_n_step_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/rewards/test_n_step_reward.py -------------------------------------------------------------------------------- /test/rewards/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/adik993/ppo-pytorch/HEAD/test/rewards/test_utils.py --------------------------------------------------------------------------------