├── .gitattributes ├── .gitignore ├── CITATION.cff ├── LICENSE ├── README.md ├── logo.PNG ├── openrl ├── __init__.py ├── agents │ ├── __init__.py │ └── base_agent.py ├── algorithms │ ├── __init__.py │ ├── a2c │ │ ├── __init__.py │ │ ├── a2c.py │ │ ├── multiprocessing_env.py │ │ └── utils.py │ ├── a3c │ │ ├── __init__.py │ │ ├── a3c_threading.py │ │ └── utils.py │ ├── actor_critic │ │ ├── __init__.py │ │ ├── actor_critic.py │ │ ├── actor_critic_simple.py │ │ ├── actor_critic_simple_two_networks.py │ │ ├── actor_critic_two_networks.py │ │ ├── vpg_to_actor_critic_Nbatches.py │ │ └── vpg_to_actor_critic_two_networks_cs295.py │ ├── bandits │ │ ├── __init__.py │ │ ├── cb_linear_ucb.py │ │ ├── cb_nn.py │ │ ├── cd_linear_ts.py │ │ ├── dataset.txt │ │ ├── epsilon_greedy.py │ │ ├── example_linucb_implementation.py │ │ ├── greedy.py │ │ ├── pure_exploration.py │ │ ├── simple_bandit_env.py │ │ ├── thompson_sampling_bernoulli.py │ │ ├── thompson_sampling_gaussian.py │ │ └── ucb.py │ ├── cql │ │ ├── __init__.py │ │ ├── cql.py │ │ ├── dqn.py │ │ ├── models.py │ │ └── utils.py │ ├── ddpg │ │ ├── __init__.py │ │ ├── ddpg.py │ │ ├── models.py │ │ └── utils.py │ ├── dqn │ │ ├── __init__.py │ │ ├── ddqn.py │ │ ├── ddqn_per.py │ │ ├── dqn.py │ │ ├── models.py │ │ └── utils.py │ ├── drqn │ │ ├── __init__.py │ │ ├── drqn.py │ │ ├── models.py │ │ └── utils.py │ ├── dyna_q │ │ ├── __init__.py │ │ ├── deep_dyna_q.py │ │ ├── dyna_q.py │ │ ├── models.py │ │ └── utils.py │ ├── fundamentals │ │ ├── __init__.py │ │ ├── monte_carlo.py │ │ ├── n_step.py │ │ ├── policy_iteration.py │ │ ├── td_lambda.py │ │ ├── td_learning.py │ │ └── value_iteration.py │ ├── imitation │ │ ├── __init__.py │ │ ├── checkpoints │ │ │ ├── checkpoint │ │ │ ├── expert_model_weights.data-00000-of-00001 │ │ │ └── expert_model_weights.index │ │ ├── expert_data.pkl │ │ ├── expert_vpg_script.py │ │ ├── imitation_learning.py │ │ └── utils.py │ ├── mbpo │ │ ├── __init__.py │ │ ├── mbpo.py │ │ ├── models.py │ │ ├── sac.py │ │ └── utils.py │ ├── mbrl │ │ ├── __init__.py │ │ ├── mbrl.py │ │ ├── models.py │ │ └── utils.py │ ├── mcts │ │ ├── __init__.py │ │ └── mcts.py │ ├── mopo │ │ ├── __init__.py │ │ ├── _mbpo2.py │ │ ├── datasets │ │ │ ├── buffer_env_obstacles_100k.pickle │ │ │ ├── buffer_env_obstacles_30k.pickle │ │ │ └── buffer_env_pendulum_10k.pickle │ │ ├── env_utils.py │ │ ├── models.py │ │ ├── mopo.py │ │ ├── online_sac.py │ │ ├── sac.py │ │ └── utils.py │ ├── morel │ │ ├── __init__.py │ │ ├── dqn.py │ │ ├── models.py │ │ ├── morel.py │ │ └── utils.py │ ├── ppo │ │ ├── PPO_Continuous.py │ │ ├── README.md │ │ ├── __init__.py │ │ ├── demo.py │ │ ├── demo_complete.py │ │ ├── multiprocessing_env.py │ │ ├── ppo.py │ │ ├── ppo_torch.py │ │ └── utils.py │ ├── reinforce │ │ ├── __init__.py │ │ ├── reinforce.py │ │ ├── reinforce_simple.py │ │ └── reinforce_simple_Nbatches.py │ ├── sac │ │ ├── __init__.py │ │ ├── models.py │ │ └── sac.py │ ├── td3 │ │ ├── __init__.py │ │ ├── models.py │ │ └── td3.py │ └── vpg │ │ ├── __init__.py │ │ ├── vpg.py │ │ ├── vpg_Nbatches.py │ │ ├── vpg_continuous.py │ │ ├── vpg_incorrect_baseline.py │ │ ├── vpg_two_networks.py │ │ └── vpg_two_networks_Nbatches.py ├── envs │ ├── __init__.py │ ├── gridworld1a.py │ ├── gridworld1b.py │ ├── gridworld2a.py │ ├── gridworld2b.py │ └── obstacles_env.py ├── models │ ├── __init__.py │ └── models.py └── util │ ├── __init__.py │ ├── compute_returns.py │ ├── plotting.py │ ├── replay_buffer.py │ └── utils.py ├── requirements.txt └── todos.txt /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/.gitignore -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/CITATION.cff -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/README.md -------------------------------------------------------------------------------- /logo.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/logo.PNG -------------------------------------------------------------------------------- /openrl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/agents/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/agents/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/agents/base_agent.py -------------------------------------------------------------------------------- /openrl/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/a2c/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/a2c/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/a2c/a2c.py -------------------------------------------------------------------------------- /openrl/algorithms/a2c/multiprocessing_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/a2c/multiprocessing_env.py -------------------------------------------------------------------------------- /openrl/algorithms/a2c/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/a2c/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/a3c/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/a3c/a3c_threading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/a3c/a3c_threading.py -------------------------------------------------------------------------------- /openrl/algorithms/a3c/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/a3c/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/actor_critic/actor_critic.py -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/actor_critic_simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/actor_critic/actor_critic_simple.py -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/actor_critic_simple_two_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/actor_critic/actor_critic_simple_two_networks.py -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/actor_critic_two_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/actor_critic/actor_critic_two_networks.py -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/vpg_to_actor_critic_Nbatches.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/actor_critic/vpg_to_actor_critic_Nbatches.py -------------------------------------------------------------------------------- /openrl/algorithms/actor_critic/vpg_to_actor_critic_two_networks_cs295.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/actor_critic/vpg_to_actor_critic_two_networks_cs295.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/bandits/cb_linear_ucb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/cb_linear_ucb.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/cb_nn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/cb_nn.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/cd_linear_ts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/cd_linear_ts.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/dataset.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/dataset.txt -------------------------------------------------------------------------------- /openrl/algorithms/bandits/epsilon_greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/epsilon_greedy.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/example_linucb_implementation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/example_linucb_implementation.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/greedy.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/pure_exploration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/pure_exploration.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/simple_bandit_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/simple_bandit_env.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/thompson_sampling_bernoulli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/thompson_sampling_bernoulli.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/thompson_sampling_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/thompson_sampling_gaussian.py -------------------------------------------------------------------------------- /openrl/algorithms/bandits/ucb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/bandits/ucb.py -------------------------------------------------------------------------------- /openrl/algorithms/cql/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/cql/cql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/cql/cql.py -------------------------------------------------------------------------------- /openrl/algorithms/cql/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/cql/dqn.py -------------------------------------------------------------------------------- /openrl/algorithms/cql/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/cql/models.py -------------------------------------------------------------------------------- /openrl/algorithms/cql/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/cql/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/ddpg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/ddpg/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ddpg/ddpg.py -------------------------------------------------------------------------------- /openrl/algorithms/ddpg/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ddpg/models.py -------------------------------------------------------------------------------- /openrl/algorithms/ddpg/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ddpg/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/dqn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/dqn/ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dqn/ddqn.py -------------------------------------------------------------------------------- /openrl/algorithms/dqn/ddqn_per.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dqn/ddqn_per.py -------------------------------------------------------------------------------- /openrl/algorithms/dqn/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dqn/dqn.py -------------------------------------------------------------------------------- /openrl/algorithms/dqn/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dqn/models.py -------------------------------------------------------------------------------- /openrl/algorithms/dqn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dqn/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/drqn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/drqn/drqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/drqn/drqn.py -------------------------------------------------------------------------------- /openrl/algorithms/drqn/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/drqn/models.py -------------------------------------------------------------------------------- /openrl/algorithms/drqn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/drqn/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/dyna_q/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/dyna_q/deep_dyna_q.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dyna_q/deep_dyna_q.py -------------------------------------------------------------------------------- /openrl/algorithms/dyna_q/dyna_q.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dyna_q/dyna_q.py -------------------------------------------------------------------------------- /openrl/algorithms/dyna_q/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dyna_q/models.py -------------------------------------------------------------------------------- /openrl/algorithms/dyna_q/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/dyna_q/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/monte_carlo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/fundamentals/monte_carlo.py -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/n_step.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/fundamentals/n_step.py -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/policy_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/fundamentals/policy_iteration.py -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/td_lambda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/fundamentals/td_lambda.py -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/td_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/fundamentals/td_learning.py -------------------------------------------------------------------------------- /openrl/algorithms/fundamentals/value_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/fundamentals/value_iteration.py -------------------------------------------------------------------------------- /openrl/algorithms/imitation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/imitation/checkpoints/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/checkpoints/checkpoint -------------------------------------------------------------------------------- /openrl/algorithms/imitation/checkpoints/expert_model_weights.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/checkpoints/expert_model_weights.data-00000-of-00001 -------------------------------------------------------------------------------- /openrl/algorithms/imitation/checkpoints/expert_model_weights.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/checkpoints/expert_model_weights.index -------------------------------------------------------------------------------- /openrl/algorithms/imitation/expert_data.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/expert_data.pkl -------------------------------------------------------------------------------- /openrl/algorithms/imitation/expert_vpg_script.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/expert_vpg_script.py -------------------------------------------------------------------------------- /openrl/algorithms/imitation/imitation_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/imitation_learning.py -------------------------------------------------------------------------------- /openrl/algorithms/imitation/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/imitation/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/mbpo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/mbpo/mbpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbpo/mbpo.py -------------------------------------------------------------------------------- /openrl/algorithms/mbpo/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbpo/models.py -------------------------------------------------------------------------------- /openrl/algorithms/mbpo/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbpo/sac.py -------------------------------------------------------------------------------- /openrl/algorithms/mbpo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbpo/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/mbrl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/mbrl/mbrl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbrl/mbrl.py -------------------------------------------------------------------------------- /openrl/algorithms/mbrl/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbrl/models.py -------------------------------------------------------------------------------- /openrl/algorithms/mbrl/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mbrl/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/mcts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/mcts/mcts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mcts/mcts.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/mopo/_mbpo2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/_mbpo2.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/datasets/buffer_env_obstacles_100k.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/datasets/buffer_env_obstacles_100k.pickle -------------------------------------------------------------------------------- /openrl/algorithms/mopo/datasets/buffer_env_obstacles_30k.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/datasets/buffer_env_obstacles_30k.pickle -------------------------------------------------------------------------------- /openrl/algorithms/mopo/datasets/buffer_env_pendulum_10k.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/datasets/buffer_env_pendulum_10k.pickle -------------------------------------------------------------------------------- /openrl/algorithms/mopo/env_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/env_utils.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/models.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/mopo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/mopo.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/online_sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/online_sac.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/sac.py -------------------------------------------------------------------------------- /openrl/algorithms/mopo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/mopo/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/morel/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/morel/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/morel/dqn.py -------------------------------------------------------------------------------- /openrl/algorithms/morel/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/morel/models.py -------------------------------------------------------------------------------- /openrl/algorithms/morel/morel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/morel/morel.py -------------------------------------------------------------------------------- /openrl/algorithms/morel/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/morel/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/PPO_Continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/PPO_Continuous.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/README.md -------------------------------------------------------------------------------- /openrl/algorithms/ppo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/ppo/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/demo.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/demo_complete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/demo_complete.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/multiprocessing_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/multiprocessing_env.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/ppo.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/ppo_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/ppo_torch.py -------------------------------------------------------------------------------- /openrl/algorithms/ppo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/ppo/utils.py -------------------------------------------------------------------------------- /openrl/algorithms/reinforce/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/reinforce/reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/reinforce/reinforce.py -------------------------------------------------------------------------------- /openrl/algorithms/reinforce/reinforce_simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/reinforce/reinforce_simple.py -------------------------------------------------------------------------------- /openrl/algorithms/reinforce/reinforce_simple_Nbatches.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/reinforce/reinforce_simple_Nbatches.py -------------------------------------------------------------------------------- /openrl/algorithms/sac/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/sac/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/sac/models.py -------------------------------------------------------------------------------- /openrl/algorithms/sac/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/sac/sac.py -------------------------------------------------------------------------------- /openrl/algorithms/td3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/td3/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/td3/models.py -------------------------------------------------------------------------------- /openrl/algorithms/td3/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/td3/td3.py -------------------------------------------------------------------------------- /openrl/algorithms/vpg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/algorithms/vpg/vpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/vpg/vpg.py -------------------------------------------------------------------------------- /openrl/algorithms/vpg/vpg_Nbatches.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/vpg/vpg_Nbatches.py -------------------------------------------------------------------------------- /openrl/algorithms/vpg/vpg_continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/vpg/vpg_continuous.py -------------------------------------------------------------------------------- /openrl/algorithms/vpg/vpg_incorrect_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/vpg/vpg_incorrect_baseline.py -------------------------------------------------------------------------------- /openrl/algorithms/vpg/vpg_two_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/vpg/vpg_two_networks.py -------------------------------------------------------------------------------- /openrl/algorithms/vpg/vpg_two_networks_Nbatches.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/algorithms/vpg/vpg_two_networks_Nbatches.py -------------------------------------------------------------------------------- /openrl/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/envs/__init__.py -------------------------------------------------------------------------------- /openrl/envs/gridworld1a.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/envs/gridworld1a.py -------------------------------------------------------------------------------- /openrl/envs/gridworld1b.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/envs/gridworld1b.py -------------------------------------------------------------------------------- /openrl/envs/gridworld2a.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/envs/gridworld2a.py -------------------------------------------------------------------------------- /openrl/envs/gridworld2b.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/envs/gridworld2b.py -------------------------------------------------------------------------------- /openrl/envs/obstacles_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/envs/obstacles_env.py -------------------------------------------------------------------------------- /openrl/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/models/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/models/models.py -------------------------------------------------------------------------------- /openrl/util/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /openrl/util/compute_returns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/util/compute_returns.py -------------------------------------------------------------------------------- /openrl/util/plotting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/util/plotting.py -------------------------------------------------------------------------------- /openrl/util/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/util/replay_buffer.py -------------------------------------------------------------------------------- /openrl/util/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/openrl/util/utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/requirements.txt -------------------------------------------------------------------------------- /todos.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/natetsang/open-rl/HEAD/todos.txt --------------------------------------------------------------------------------