├── .flake8 ├── .github └── ISSUE_TEMPLATE.md ├── .gitignore ├── .isort.cfg ├── .pre-commit-config.yaml ├── LICENSE ├── README.md ├── benchmark ├── a2c │ ├── .result │ │ ├── result_a2c_torch0.png │ │ └── result_a2c_torch1.png │ ├── README.md │ ├── a2c_config.py │ ├── actor.py │ ├── atari_agent.py │ ├── atari_model.py │ └── train.py ├── ddpg │ ├── README.md │ ├── mujoco_agent.py │ ├── mujoco_model.py │ └── train.py ├── dqn │ ├── README.md │ ├── agent.py │ ├── model.py │ ├── replay_memory.py │ └── train.py ├── ppo │ ├── README.md │ ├── agent.py │ ├── atari_config.py │ ├── atari_model.py │ ├── env_utils.py │ ├── storage.py │ └── train.py └── quickstart │ ├── cartpole_agent.py │ ├── cartpole_model.py │ └── train.py ├── docs ├── Actor-Critic.md ├── MADDPG.md ├── MAPPO.assets │ ├── 0460dffdf8be4326a4b436dfc8699b6d.png │ ├── 2021071021274089.png │ ├── 20210710220735586.png │ ├── 2074dc24b0ea438eb81972d146727062.png │ ├── 59097a747afd4da2836b931aced5d66d.png │ ├── 84ffdc2f403a4103b3c65873290a5690.png │ ├── 8ea17f2b8e304794b78bf92133dffec4.png │ ├── cd48373eef194828b8bd518b7224f824.png │ ├── ef7ae300e9584fea9e882e56cc86c414.png │ └── mappo_1.jpg ├── MAPPO.md ├── awesome_rl_algo.md ├── awesome_rl_en.md ├── images │ ├── Breakout.gif │ ├── Half-Cheetah.gif │ ├── abstractions.png │ ├── algorithms.png │ ├── logo.png │ ├── performance.gif │ └── trained.gif ├── 强化学习入门指南.md ├── 强化学习框架指南.md ├── 强化学习算法选择.md ├── 强化学习调参指南.md └── 星际争霸.md ├── examples ├── deep-rl-class │ ├── antbullet_a2c.py │ ├── cartpole_rainforce.py │ ├── frozen_lake_v1.py │ ├── load_from_hub.py │ ├── pixelcopter_rainforce.py │ ├── taxi-v3.py │ └── walker2d_a2c.py ├── gym_atari.py ├── gym_example.py ├── hands-on-rl │ ├── actor-critic.py │ ├── base_concept │ │ ├── Cliff_Walking.py │ │ ├── markov_decision_process.py │ │ └── multi_armed_bandit.py │ ├── behavior_cloning.py │ ├── ddpg.py │ ├── ddqn.py │ ├── dqn.py │ ├── dueling_dqn.py │ ├── gail.py │ ├── ippo.py │ ├── maddpg.py │ ├── ppo.py │ ├── ppo_continuous.py │ ├── rainforce.py │ ├── sac.py │ ├── sac_continuous.py │ ├── trpo.py │ └── trpo_continuous.py ├── marl │ ├── coma │ │ ├── .benchmark │ │ │ └── 3m_result.png │ │ ├── README.md │ │ ├── coma_config.py │ │ ├── sc2_agent.py │ │ ├── sc2_model.py │ │ ├── starcraft2 │ │ │ ├── Dockerfile │ │ │ ├── build_docker.sh │ │ │ └── install_sc2.sh │ │ └── train.py │ ├── mappo │ │ ├── README.md │ │ ├── env_wrappers.py │ │ ├── mappo_buffer.py │ │ ├── simple_agent.py │ │ ├── simple_model.py │ │ └── train.py │ ├── qmix │ │ ├── README.md │ │ ├── arguments.py │ │ ├── env_wrapper.py │ │ ├── images │ │ │ └── torch-qmix-result.png │ │ ├── main.py │ │ ├── qmix_agent.py │ │ ├── qmix_config.py │ │ ├── qmixer_model.py │ │ ├── replay_buffer.py │ │ ├── rnn_model.py │ │ ├── run.sh │ │ └── utils.py │ └── vdn │ │ ├── arguments.py │ │ ├── main.py │ │ ├── run.sh │ │ ├── utils.py │ │ ├── vdn_agent.py │ │ ├── vdn_config.py │ │ └── vdn_net.py ├── petting_smac.py ├── smac_demo.py └── tutorials │ ├── Actor-Critic │ ├── agent.py │ └── train.py │ ├── C51 │ ├── agent.py │ └── train.py │ ├── DDPG-BipedalWalker │ ├── README.md │ ├── ddpg_agent.py │ ├── model.py │ └── train.py │ ├── DDPG-Pendulum │ ├── agent.py │ └── train.py │ ├── DQN-Atari │ ├── agent.py │ ├── network.py │ ├── replay_memory.py │ └── train.py │ ├── DQN-dist │ ├── agent.py │ ├── main.py │ ├── network.py │ └── train.py │ ├── DQN │ ├── agent.py │ ├── network.py │ └── train.py │ ├── Multi-Agent │ ├── README.md │ ├── idqn │ │ ├── agent.py │ │ └── train.py │ ├── ma-gym.py │ ├── maddpg │ │ ├── agent.py │ │ └── train.py │ └── vdn │ │ ├── agent.py │ │ └── train.py │ ├── N-step-DQN │ ├── agent.py │ ├── network.py │ └── train.py │ ├── Noisy-DQN │ ├── agent.py │ └── train.py │ ├── PPO │ ├── agent.py │ └── train.py │ ├── Policy-Gradient │ ├── agent.py │ └── train.py │ ├── README.md │ ├── Rainbow │ ├── agent.py │ └── train.py │ ├── SAC │ ├── agent.py │ └── train.py │ ├── SAC_Continuous │ ├── agent.py │ └── train.py │ ├── TD3 │ ├── agent.py │ ├── agent_bound.py │ └── train.py │ ├── TRPO │ ├── agent.py │ └── train.py │ ├── assets │ └── img │ │ ├── antbullet.gif │ │ ├── breakout.gif │ │ ├── cartpole.jpg │ │ ├── frozenlake.gif │ │ ├── huggy.jpg │ │ ├── lunarlander.gif │ │ ├── pixelcopter.jpg │ │ ├── pong.jpg │ │ ├── qbert.gif │ │ ├── seaquest.gif │ │ ├── snowballfight.gif │ │ ├── spaceinvaders.gif │ │ ├── taxi.gif │ │ └── walker2d.gif │ ├── basic-rl │ ├── dyna-q │ │ ├── agent.py │ │ ├── gridworld.py │ │ └── train.py │ ├── gridworld.py │ ├── gym_example.py │ ├── q_learning │ │ ├── agent.py │ │ ├── gridworld.py │ │ └── train.py │ ├── q_learning_frozenlake │ │ ├── agent.py │ │ ├── gridworld.py │ │ └── train.py │ ├── sarsa │ │ ├── agent.py │ │ ├── gridworld.py │ │ └── train.py │ └── sarsa_frozenlake │ │ ├── agent.py │ │ ├── gridworld.py │ │ └── train.py │ ├── policy_gradient │ ├── a2c.py │ ├── ddpg.py │ ├── ppo.py │ ├── sac.py │ └── td3.py │ └── rainbow │ ├── categorical_dqn.py │ ├── ddqn.py │ ├── duling_network.py │ ├── multistep_dqn.py │ ├── noise_network.py │ ├── rainbow.py │ └── segment_tree.py ├── requirements.txt ├── rltoolkit ├── __init__.py ├── __version__.py ├── agent │ ├── __init__.py │ ├── base_agent.py │ └── distributions.py ├── data │ ├── __init__.py │ ├── buffer │ │ ├── __init__.py │ │ ├── ma_replaybuffer.py │ │ ├── replaybuffer.py │ │ └── storage.py │ └── utils │ │ ├── __init__.py │ │ └── segment_tree.py ├── env │ ├── __init__.py │ ├── atari_wrapper.py │ ├── atari_wrappers.py │ ├── continuous_wrappers.py │ ├── gym_envs.py │ ├── mujoco_wrappers.py │ ├── multiagent_env.py │ ├── multiagent_simple_env.py │ ├── preprocessing.py │ └── vector_env.py ├── models │ ├── __init__.py │ ├── base_model.py │ ├── net.py │ ├── noisynet.py │ ├── ounoise.py │ ├── random.py │ └── utils.py ├── policy │ ├── __init__.py │ ├── base_policy.py │ ├── modelbased │ │ └── __init__.py │ ├── modelfree │ │ ├── __init__.py │ │ ├── a2c.py │ │ ├── a2c_acktr.py │ │ ├── cql.py │ │ ├── ddpg.py │ │ ├── ddqn.py │ │ ├── dqn.py │ │ ├── iql.py │ │ ├── oac.py │ │ ├── policy_gradient.py │ │ ├── ppo.py │ │ ├── ppov2.py │ │ ├── sac.py │ │ └── td3.py │ └── multiagent │ │ ├── __init__.py │ │ ├── coma.py │ │ ├── maddpg.py │ │ ├── mappo.py │ │ └── qmix.py ├── trainer │ ├── __init__.py │ ├── arguments.py │ └── evaluation.py └── utils │ ├── __init__.py │ ├── kfac.py │ ├── logger │ ├── __init__.py │ ├── base.py │ ├── logging.py │ ├── logs.py │ ├── tensorboard.py │ └── wandb.py │ ├── lr_scheduler.py │ ├── name_dict.py │ ├── progressbar.py │ ├── rl_utils.py │ ├── timer.py │ └── utils.py └── scripts ├── creat_job.py └── creat_job.sh /.flake8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/.flake8 -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/.github/ISSUE_TEMPLATE.md -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/.gitignore -------------------------------------------------------------------------------- /.isort.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/.isort.cfg -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/README.md -------------------------------------------------------------------------------- /benchmark/a2c/.result/result_a2c_torch0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/.result/result_a2c_torch0.png -------------------------------------------------------------------------------- /benchmark/a2c/.result/result_a2c_torch1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/.result/result_a2c_torch1.png -------------------------------------------------------------------------------- /benchmark/a2c/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/README.md -------------------------------------------------------------------------------- /benchmark/a2c/a2c_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/a2c_config.py -------------------------------------------------------------------------------- /benchmark/a2c/actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/actor.py -------------------------------------------------------------------------------- /benchmark/a2c/atari_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/atari_agent.py -------------------------------------------------------------------------------- /benchmark/a2c/atari_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/atari_model.py -------------------------------------------------------------------------------- /benchmark/a2c/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/a2c/train.py -------------------------------------------------------------------------------- /benchmark/ddpg/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ddpg/README.md -------------------------------------------------------------------------------- /benchmark/ddpg/mujoco_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ddpg/mujoco_agent.py -------------------------------------------------------------------------------- /benchmark/ddpg/mujoco_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ddpg/mujoco_model.py -------------------------------------------------------------------------------- /benchmark/ddpg/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ddpg/train.py -------------------------------------------------------------------------------- /benchmark/dqn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/dqn/README.md -------------------------------------------------------------------------------- /benchmark/dqn/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/dqn/agent.py -------------------------------------------------------------------------------- /benchmark/dqn/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/dqn/model.py -------------------------------------------------------------------------------- /benchmark/dqn/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/dqn/replay_memory.py -------------------------------------------------------------------------------- /benchmark/dqn/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/dqn/train.py -------------------------------------------------------------------------------- /benchmark/ppo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/README.md -------------------------------------------------------------------------------- /benchmark/ppo/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/agent.py -------------------------------------------------------------------------------- /benchmark/ppo/atari_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/atari_config.py -------------------------------------------------------------------------------- /benchmark/ppo/atari_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/atari_model.py -------------------------------------------------------------------------------- /benchmark/ppo/env_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/env_utils.py -------------------------------------------------------------------------------- /benchmark/ppo/storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/storage.py -------------------------------------------------------------------------------- /benchmark/ppo/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/ppo/train.py -------------------------------------------------------------------------------- /benchmark/quickstart/cartpole_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/quickstart/cartpole_agent.py -------------------------------------------------------------------------------- /benchmark/quickstart/cartpole_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/quickstart/cartpole_model.py -------------------------------------------------------------------------------- /benchmark/quickstart/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/benchmark/quickstart/train.py -------------------------------------------------------------------------------- /docs/Actor-Critic.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/Actor-Critic.md -------------------------------------------------------------------------------- /docs/MADDPG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MADDPG.md -------------------------------------------------------------------------------- /docs/MAPPO.assets/0460dffdf8be4326a4b436dfc8699b6d.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/0460dffdf8be4326a4b436dfc8699b6d.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/2021071021274089.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/2021071021274089.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/20210710220735586.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/20210710220735586.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/2074dc24b0ea438eb81972d146727062.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/2074dc24b0ea438eb81972d146727062.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/59097a747afd4da2836b931aced5d66d.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/59097a747afd4da2836b931aced5d66d.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/84ffdc2f403a4103b3c65873290a5690.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/84ffdc2f403a4103b3c65873290a5690.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/8ea17f2b8e304794b78bf92133dffec4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/8ea17f2b8e304794b78bf92133dffec4.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/cd48373eef194828b8bd518b7224f824.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/cd48373eef194828b8bd518b7224f824.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/ef7ae300e9584fea9e882e56cc86c414.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/ef7ae300e9584fea9e882e56cc86c414.png -------------------------------------------------------------------------------- /docs/MAPPO.assets/mappo_1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.assets/mappo_1.jpg -------------------------------------------------------------------------------- /docs/MAPPO.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/MAPPO.md -------------------------------------------------------------------------------- /docs/awesome_rl_algo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/awesome_rl_algo.md -------------------------------------------------------------------------------- /docs/awesome_rl_en.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/awesome_rl_en.md -------------------------------------------------------------------------------- /docs/images/Breakout.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/Breakout.gif -------------------------------------------------------------------------------- /docs/images/Half-Cheetah.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/Half-Cheetah.gif -------------------------------------------------------------------------------- /docs/images/abstractions.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/abstractions.png -------------------------------------------------------------------------------- /docs/images/algorithms.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/algorithms.png -------------------------------------------------------------------------------- /docs/images/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/logo.png -------------------------------------------------------------------------------- /docs/images/performance.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/performance.gif -------------------------------------------------------------------------------- /docs/images/trained.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/images/trained.gif -------------------------------------------------------------------------------- /docs/强化学习入门指南.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/强化学习入门指南.md -------------------------------------------------------------------------------- /docs/强化学习框架指南.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/强化学习框架指南.md -------------------------------------------------------------------------------- /docs/强化学习算法选择.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/强化学习算法选择.md -------------------------------------------------------------------------------- /docs/强化学习调参指南.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/强化学习调参指南.md -------------------------------------------------------------------------------- /docs/星际争霸.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/docs/星际争霸.md -------------------------------------------------------------------------------- /examples/deep-rl-class/antbullet_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/antbullet_a2c.py -------------------------------------------------------------------------------- /examples/deep-rl-class/cartpole_rainforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/cartpole_rainforce.py -------------------------------------------------------------------------------- /examples/deep-rl-class/frozen_lake_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/frozen_lake_v1.py -------------------------------------------------------------------------------- /examples/deep-rl-class/load_from_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/load_from_hub.py -------------------------------------------------------------------------------- /examples/deep-rl-class/pixelcopter_rainforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/pixelcopter_rainforce.py -------------------------------------------------------------------------------- /examples/deep-rl-class/taxi-v3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/taxi-v3.py -------------------------------------------------------------------------------- /examples/deep-rl-class/walker2d_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/deep-rl-class/walker2d_a2c.py -------------------------------------------------------------------------------- /examples/gym_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/gym_atari.py -------------------------------------------------------------------------------- /examples/gym_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/gym_example.py -------------------------------------------------------------------------------- /examples/hands-on-rl/actor-critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/actor-critic.py -------------------------------------------------------------------------------- /examples/hands-on-rl/base_concept/Cliff_Walking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/base_concept/Cliff_Walking.py -------------------------------------------------------------------------------- /examples/hands-on-rl/base_concept/markov_decision_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/base_concept/markov_decision_process.py -------------------------------------------------------------------------------- /examples/hands-on-rl/base_concept/multi_armed_bandit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/base_concept/multi_armed_bandit.py -------------------------------------------------------------------------------- /examples/hands-on-rl/behavior_cloning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/behavior_cloning.py -------------------------------------------------------------------------------- /examples/hands-on-rl/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/ddpg.py -------------------------------------------------------------------------------- /examples/hands-on-rl/ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/ddqn.py -------------------------------------------------------------------------------- /examples/hands-on-rl/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/dqn.py -------------------------------------------------------------------------------- /examples/hands-on-rl/dueling_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/dueling_dqn.py -------------------------------------------------------------------------------- /examples/hands-on-rl/gail.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/gail.py -------------------------------------------------------------------------------- /examples/hands-on-rl/ippo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/ippo.py -------------------------------------------------------------------------------- /examples/hands-on-rl/maddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/maddpg.py -------------------------------------------------------------------------------- /examples/hands-on-rl/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/ppo.py -------------------------------------------------------------------------------- /examples/hands-on-rl/ppo_continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/ppo_continuous.py -------------------------------------------------------------------------------- /examples/hands-on-rl/rainforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/rainforce.py -------------------------------------------------------------------------------- /examples/hands-on-rl/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/sac.py -------------------------------------------------------------------------------- /examples/hands-on-rl/sac_continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/sac_continuous.py -------------------------------------------------------------------------------- /examples/hands-on-rl/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/trpo.py -------------------------------------------------------------------------------- /examples/hands-on-rl/trpo_continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/hands-on-rl/trpo_continuous.py -------------------------------------------------------------------------------- /examples/marl/coma/.benchmark/3m_result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/.benchmark/3m_result.png -------------------------------------------------------------------------------- /examples/marl/coma/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/README.md -------------------------------------------------------------------------------- /examples/marl/coma/coma_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/coma_config.py -------------------------------------------------------------------------------- /examples/marl/coma/sc2_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/sc2_agent.py -------------------------------------------------------------------------------- /examples/marl/coma/sc2_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/sc2_model.py -------------------------------------------------------------------------------- /examples/marl/coma/starcraft2/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/starcraft2/Dockerfile -------------------------------------------------------------------------------- /examples/marl/coma/starcraft2/build_docker.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/starcraft2/build_docker.sh -------------------------------------------------------------------------------- /examples/marl/coma/starcraft2/install_sc2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/starcraft2/install_sc2.sh -------------------------------------------------------------------------------- /examples/marl/coma/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/coma/train.py -------------------------------------------------------------------------------- /examples/marl/mappo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/mappo/README.md -------------------------------------------------------------------------------- /examples/marl/mappo/env_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/mappo/env_wrappers.py -------------------------------------------------------------------------------- /examples/marl/mappo/mappo_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/mappo/mappo_buffer.py -------------------------------------------------------------------------------- /examples/marl/mappo/simple_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/mappo/simple_agent.py -------------------------------------------------------------------------------- /examples/marl/mappo/simple_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/mappo/simple_model.py -------------------------------------------------------------------------------- /examples/marl/mappo/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/mappo/train.py -------------------------------------------------------------------------------- /examples/marl/qmix/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/README.md -------------------------------------------------------------------------------- /examples/marl/qmix/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/arguments.py -------------------------------------------------------------------------------- /examples/marl/qmix/env_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/env_wrapper.py -------------------------------------------------------------------------------- /examples/marl/qmix/images/torch-qmix-result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/images/torch-qmix-result.png -------------------------------------------------------------------------------- /examples/marl/qmix/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/main.py -------------------------------------------------------------------------------- /examples/marl/qmix/qmix_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/qmix_agent.py -------------------------------------------------------------------------------- /examples/marl/qmix/qmix_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/qmix_config.py -------------------------------------------------------------------------------- /examples/marl/qmix/qmixer_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/qmixer_model.py -------------------------------------------------------------------------------- /examples/marl/qmix/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/replay_buffer.py -------------------------------------------------------------------------------- /examples/marl/qmix/rnn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/rnn_model.py -------------------------------------------------------------------------------- /examples/marl/qmix/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/run.sh -------------------------------------------------------------------------------- /examples/marl/qmix/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/qmix/utils.py -------------------------------------------------------------------------------- /examples/marl/vdn/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/arguments.py -------------------------------------------------------------------------------- /examples/marl/vdn/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/main.py -------------------------------------------------------------------------------- /examples/marl/vdn/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/run.sh -------------------------------------------------------------------------------- /examples/marl/vdn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/utils.py -------------------------------------------------------------------------------- /examples/marl/vdn/vdn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/vdn_agent.py -------------------------------------------------------------------------------- /examples/marl/vdn/vdn_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/vdn_config.py -------------------------------------------------------------------------------- /examples/marl/vdn/vdn_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/marl/vdn/vdn_net.py -------------------------------------------------------------------------------- /examples/petting_smac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/petting_smac.py -------------------------------------------------------------------------------- /examples/smac_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/smac_demo.py -------------------------------------------------------------------------------- /examples/tutorials/Actor-Critic/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Actor-Critic/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Actor-Critic/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Actor-Critic/train.py -------------------------------------------------------------------------------- /examples/tutorials/C51/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/C51/agent.py -------------------------------------------------------------------------------- /examples/tutorials/C51/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/C51/train.py -------------------------------------------------------------------------------- /examples/tutorials/DDPG-BipedalWalker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DDPG-BipedalWalker/README.md -------------------------------------------------------------------------------- /examples/tutorials/DDPG-BipedalWalker/ddpg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DDPG-BipedalWalker/ddpg_agent.py -------------------------------------------------------------------------------- /examples/tutorials/DDPG-BipedalWalker/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DDPG-BipedalWalker/model.py -------------------------------------------------------------------------------- /examples/tutorials/DDPG-BipedalWalker/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DDPG-BipedalWalker/train.py -------------------------------------------------------------------------------- /examples/tutorials/DDPG-Pendulum/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DDPG-Pendulum/agent.py -------------------------------------------------------------------------------- /examples/tutorials/DDPG-Pendulum/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DDPG-Pendulum/train.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-Atari/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-Atari/agent.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-Atari/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-Atari/network.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-Atari/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-Atari/replay_memory.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-Atari/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-Atari/train.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-dist/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-dist/agent.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-dist/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-dist/main.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-dist/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-dist/network.py -------------------------------------------------------------------------------- /examples/tutorials/DQN-dist/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN-dist/train.py -------------------------------------------------------------------------------- /examples/tutorials/DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN/agent.py -------------------------------------------------------------------------------- /examples/tutorials/DQN/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN/network.py -------------------------------------------------------------------------------- /examples/tutorials/DQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/DQN/train.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/README.md -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/idqn/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/idqn/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/idqn/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/idqn/train.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/ma-gym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/ma-gym.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/maddpg/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/maddpg/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/maddpg/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/maddpg/train.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/vdn/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/vdn/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Multi-Agent/vdn/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Multi-Agent/vdn/train.py -------------------------------------------------------------------------------- /examples/tutorials/N-step-DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/N-step-DQN/agent.py -------------------------------------------------------------------------------- /examples/tutorials/N-step-DQN/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/N-step-DQN/network.py -------------------------------------------------------------------------------- /examples/tutorials/N-step-DQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/N-step-DQN/train.py -------------------------------------------------------------------------------- /examples/tutorials/Noisy-DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Noisy-DQN/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Noisy-DQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Noisy-DQN/train.py -------------------------------------------------------------------------------- /examples/tutorials/PPO/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/PPO/agent.py -------------------------------------------------------------------------------- /examples/tutorials/PPO/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/PPO/train.py -------------------------------------------------------------------------------- /examples/tutorials/Policy-Gradient/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Policy-Gradient/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Policy-Gradient/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Policy-Gradient/train.py -------------------------------------------------------------------------------- /examples/tutorials/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/README.md -------------------------------------------------------------------------------- /examples/tutorials/Rainbow/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Rainbow/agent.py -------------------------------------------------------------------------------- /examples/tutorials/Rainbow/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/Rainbow/train.py -------------------------------------------------------------------------------- /examples/tutorials/SAC/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/SAC/agent.py -------------------------------------------------------------------------------- /examples/tutorials/SAC/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/SAC/train.py -------------------------------------------------------------------------------- /examples/tutorials/SAC_Continuous/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/SAC_Continuous/agent.py -------------------------------------------------------------------------------- /examples/tutorials/SAC_Continuous/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/SAC_Continuous/train.py -------------------------------------------------------------------------------- /examples/tutorials/TD3/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/TD3/agent.py -------------------------------------------------------------------------------- /examples/tutorials/TD3/agent_bound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/TD3/agent_bound.py -------------------------------------------------------------------------------- /examples/tutorials/TD3/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/TD3/train.py -------------------------------------------------------------------------------- /examples/tutorials/TRPO/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/TRPO/agent.py -------------------------------------------------------------------------------- /examples/tutorials/TRPO/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/TRPO/train.py -------------------------------------------------------------------------------- /examples/tutorials/assets/img/antbullet.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/antbullet.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/breakout.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/breakout.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/cartpole.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/cartpole.jpg -------------------------------------------------------------------------------- /examples/tutorials/assets/img/frozenlake.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/frozenlake.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/huggy.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/huggy.jpg -------------------------------------------------------------------------------- /examples/tutorials/assets/img/lunarlander.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/lunarlander.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/pixelcopter.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/pixelcopter.jpg -------------------------------------------------------------------------------- /examples/tutorials/assets/img/pong.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/pong.jpg -------------------------------------------------------------------------------- /examples/tutorials/assets/img/qbert.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/qbert.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/seaquest.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/seaquest.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/snowballfight.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/snowballfight.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/spaceinvaders.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/spaceinvaders.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/taxi.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/taxi.gif -------------------------------------------------------------------------------- /examples/tutorials/assets/img/walker2d.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/assets/img/walker2d.gif -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/dyna-q/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/dyna-q/agent.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/dyna-q/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/dyna-q/gridworld.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/dyna-q/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/dyna-q/train.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/gridworld.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/gym_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/gym_example.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/q_learning/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/q_learning/agent.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/q_learning/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/q_learning/gridworld.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/q_learning/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/q_learning/train.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/q_learning_frozenlake/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/q_learning_frozenlake/agent.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/q_learning_frozenlake/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/q_learning_frozenlake/gridworld.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/q_learning_frozenlake/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/q_learning_frozenlake/train.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/sarsa/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/sarsa/agent.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/sarsa/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/sarsa/gridworld.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/sarsa/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/sarsa/train.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/sarsa_frozenlake/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/sarsa_frozenlake/agent.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/sarsa_frozenlake/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/sarsa_frozenlake/gridworld.py -------------------------------------------------------------------------------- /examples/tutorials/basic-rl/sarsa_frozenlake/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/basic-rl/sarsa_frozenlake/train.py -------------------------------------------------------------------------------- /examples/tutorials/policy_gradient/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/policy_gradient/a2c.py -------------------------------------------------------------------------------- /examples/tutorials/policy_gradient/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/policy_gradient/ddpg.py -------------------------------------------------------------------------------- /examples/tutorials/policy_gradient/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/policy_gradient/ppo.py -------------------------------------------------------------------------------- /examples/tutorials/policy_gradient/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/policy_gradient/sac.py -------------------------------------------------------------------------------- /examples/tutorials/policy_gradient/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/policy_gradient/td3.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/categorical_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/categorical_dqn.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/ddqn.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/duling_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/duling_network.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/multistep_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/multistep_dqn.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/noise_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/noise_network.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/rainbow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/rainbow.py -------------------------------------------------------------------------------- /examples/tutorials/rainbow/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/examples/tutorials/rainbow/segment_tree.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/requirements.txt -------------------------------------------------------------------------------- /rltoolkit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/__version__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/__version__.py -------------------------------------------------------------------------------- /rltoolkit/agent/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/agent/__init__.py -------------------------------------------------------------------------------- /rltoolkit/agent/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/agent/base_agent.py -------------------------------------------------------------------------------- /rltoolkit/agent/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/agent/distributions.py -------------------------------------------------------------------------------- /rltoolkit/data/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/data/buffer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/data/buffer/__init__.py -------------------------------------------------------------------------------- /rltoolkit/data/buffer/ma_replaybuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/data/buffer/ma_replaybuffer.py -------------------------------------------------------------------------------- /rltoolkit/data/buffer/replaybuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/data/buffer/replaybuffer.py -------------------------------------------------------------------------------- /rltoolkit/data/buffer/storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/data/buffer/storage.py -------------------------------------------------------------------------------- /rltoolkit/data/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/data/utils/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/data/utils/segment_tree.py -------------------------------------------------------------------------------- /rltoolkit/env/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/env/atari_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/atari_wrapper.py -------------------------------------------------------------------------------- /rltoolkit/env/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/atari_wrappers.py -------------------------------------------------------------------------------- /rltoolkit/env/continuous_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/continuous_wrappers.py -------------------------------------------------------------------------------- /rltoolkit/env/gym_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/gym_envs.py -------------------------------------------------------------------------------- /rltoolkit/env/mujoco_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/mujoco_wrappers.py -------------------------------------------------------------------------------- /rltoolkit/env/multiagent_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/multiagent_env.py -------------------------------------------------------------------------------- /rltoolkit/env/multiagent_simple_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/multiagent_simple_env.py -------------------------------------------------------------------------------- /rltoolkit/env/preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/preprocessing.py -------------------------------------------------------------------------------- /rltoolkit/env/vector_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/env/vector_env.py -------------------------------------------------------------------------------- /rltoolkit/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/__init__.py -------------------------------------------------------------------------------- /rltoolkit/models/base_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/base_model.py -------------------------------------------------------------------------------- /rltoolkit/models/net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/net.py -------------------------------------------------------------------------------- /rltoolkit/models/noisynet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/noisynet.py -------------------------------------------------------------------------------- /rltoolkit/models/ounoise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/ounoise.py -------------------------------------------------------------------------------- /rltoolkit/models/random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/random.py -------------------------------------------------------------------------------- /rltoolkit/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/models/utils.py -------------------------------------------------------------------------------- /rltoolkit/policy/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/policy/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/base_policy.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelbased/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/__init__.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/a2c.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/a2c_acktr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/a2c_acktr.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/cql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/cql.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/ddpg.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/ddqn.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/dqn.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/iql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/iql.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/oac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/oac.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/policy_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/policy_gradient.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/ppo.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/ppov2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/ppov2.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/sac.py -------------------------------------------------------------------------------- /rltoolkit/policy/modelfree/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/modelfree/td3.py -------------------------------------------------------------------------------- /rltoolkit/policy/multiagent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/policy/multiagent/coma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/multiagent/coma.py -------------------------------------------------------------------------------- /rltoolkit/policy/multiagent/maddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/multiagent/maddpg.py -------------------------------------------------------------------------------- /rltoolkit/policy/multiagent/mappo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/multiagent/mappo.py -------------------------------------------------------------------------------- /rltoolkit/policy/multiagent/qmix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/policy/multiagent/qmix.py -------------------------------------------------------------------------------- /rltoolkit/trainer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/trainer/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/trainer/arguments.py -------------------------------------------------------------------------------- /rltoolkit/trainer/evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/trainer/evaluation.py -------------------------------------------------------------------------------- /rltoolkit/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/__init__.py -------------------------------------------------------------------------------- /rltoolkit/utils/kfac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/kfac.py -------------------------------------------------------------------------------- /rltoolkit/utils/logger/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rltoolkit/utils/logger/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/logger/base.py -------------------------------------------------------------------------------- /rltoolkit/utils/logger/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/logger/logging.py -------------------------------------------------------------------------------- /rltoolkit/utils/logger/logs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/logger/logs.py -------------------------------------------------------------------------------- /rltoolkit/utils/logger/tensorboard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/logger/tensorboard.py -------------------------------------------------------------------------------- /rltoolkit/utils/logger/wandb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/logger/wandb.py -------------------------------------------------------------------------------- /rltoolkit/utils/lr_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/lr_scheduler.py -------------------------------------------------------------------------------- /rltoolkit/utils/name_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/name_dict.py -------------------------------------------------------------------------------- /rltoolkit/utils/progressbar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/progressbar.py -------------------------------------------------------------------------------- /rltoolkit/utils/rl_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/rl_utils.py -------------------------------------------------------------------------------- /rltoolkit/utils/timer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/timer.py -------------------------------------------------------------------------------- /rltoolkit/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/rltoolkit/utils/utils.py -------------------------------------------------------------------------------- /scripts/creat_job.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jianzhnie/RLToolkit/HEAD/scripts/creat_job.py -------------------------------------------------------------------------------- /scripts/creat_job.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | 4 | nohup python creat_job.py > output.txt 2>&1 & 5 | --------------------------------------------------------------------------------