├── .gitignore ├── APF.py ├── BA.py ├── LICENSE ├── README.md ├── config ├── config_DQN.json └── config_IQN.json ├── cvar_distributions.png ├── env_visualizer.py ├── marinenav_env ├── __init__.py ├── envs │ ├── __init__.py │ ├── marinenav_env.py │ └── utils │ │ └── robot.py └── setup.py ├── pretrained_models ├── DQN │ └── seed_3 │ │ ├── best_model.zip │ │ ├── evaluations.npz │ │ ├── latest_model.zip │ │ ├── training_schedule.json │ │ └── trial_config.json └── IQN │ └── seed_3 │ ├── adaptive_evaluations.npz │ ├── constructor_params.json │ ├── eval_config.json │ ├── greedy_evaluations.npz │ ├── network_params.pth │ ├── training_schedule.json │ └── trial_config.json ├── run_experiments.py ├── scripts ├── plot_eval_returns.py ├── visualize_IQN_eval_episode.py └── visualize_exp_episode.py ├── system_requirements ├── thirdparty ├── IQN │ ├── __init__.py │ ├── agent.py │ ├── model.py │ └── replay_buffer.py ├── __init__.py ├── sb3_contrib │ ├── __init__.py │ ├── ars │ │ ├── __init__.py │ │ ├── ars.py │ │ └── policies.py │ ├── common │ │ ├── __init__.py │ │ ├── envs │ │ │ ├── __init__.py │ │ │ └── invalid_actions_env.py │ │ ├── maskable │ │ │ ├── __init__.py │ │ │ ├── buffers.py │ │ │ ├── callbacks.py │ │ │ ├── distributions.py │ │ │ ├── evaluation.py │ │ │ ├── policies.py │ │ │ └── utils.py │ │ ├── recurrent │ │ │ ├── __init__.py │ │ │ ├── buffers.py │ │ │ ├── policies.py │ │ │ └── type_aliases.py │ │ ├── utils.py │ │ ├── vec_env │ │ │ ├── __init__.py │ │ │ └── async_eval.py │ │ └── wrappers │ │ │ ├── __init__.py │ │ │ ├── action_masker.py │ │ │ └── time_feature.py │ ├── ppo_mask │ │ ├── __init__.py │ │ ├── policies.py │ │ └── ppo_mask.py │ ├── ppo_recurrent │ │ ├── __init__.py │ │ ├── policies.py │ │ └── ppo_recurrent.py │ ├── py.typed │ ├── qrdqn │ │ ├── __init__.py │ │ ├── policies.py │ │ └── qrdqn.py │ ├── tqc │ │ ├── __init__.py │ │ ├── policies.py │ │ └── tqc.py │ ├── trpo │ │ ├── __init__.py │ │ ├── policies.py │ │ └── trpo.py │ └── version.txt └── stable_baselines3 │ ├── __init__.py │ ├── a2c │ ├── __init__.py │ ├── a2c.py │ └── policies.py │ ├── common │ ├── __init__.py │ ├── atari_wrappers.py │ ├── base_class.py │ ├── buffers.py │ ├── callbacks.py │ ├── distributions.py │ ├── env_checker.py │ ├── env_util.py │ ├── envs │ │ ├── __init__.py │ │ ├── bit_flipping_env.py │ │ ├── identity_env.py │ │ └── multi_input_envs.py │ ├── evaluation.py │ ├── logger.py │ ├── monitor.py │ ├── noise.py │ ├── off_policy_algorithm.py │ ├── on_policy_algorithm.py │ ├── policies.py │ ├── preprocessing.py │ ├── results_plotter.py │ ├── running_mean_std.py │ ├── save_util.py │ ├── sb2_compat │ │ ├── __init__.py │ │ └── rmsprop_tf_like.py │ ├── torch_layers.py │ ├── type_aliases.py │ ├── utils.py │ └── vec_env │ │ ├── __init__.py │ │ ├── base_vec_env.py │ │ ├── dummy_vec_env.py │ │ ├── stacked_observations.py │ │ ├── subproc_vec_env.py │ │ ├── util.py │ │ ├── vec_check_nan.py │ │ ├── vec_extract_dict_obs.py │ │ ├── vec_frame_stack.py │ │ ├── vec_monitor.py │ │ ├── vec_normalize.py │ │ ├── vec_transpose.py │ │ └── vec_video_recorder.py │ ├── ddpg │ ├── __init__.py │ ├── ddpg.py │ └── policies.py │ ├── dqn │ ├── __init__.py │ ├── dqn.py │ └── policies.py │ ├── her │ ├── __init__.py │ ├── goal_selection_strategy.py │ └── her_replay_buffer.py │ ├── ppo │ ├── __init__.py │ ├── policies.py │ └── ppo.py │ ├── py.typed │ ├── sac │ ├── __init__.py │ ├── policies.py │ └── sac.py │ ├── td3 │ ├── __init__.py │ ├── policies.py │ └── td3.py │ └── version.txt ├── train_IQN_model.py └── train_sb3_model.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/.gitignore -------------------------------------------------------------------------------- /APF.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/APF.py -------------------------------------------------------------------------------- /BA.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/BA.py -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/README.md -------------------------------------------------------------------------------- /config/config_DQN.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/config/config_DQN.json -------------------------------------------------------------------------------- /config/config_IQN.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/config/config_IQN.json -------------------------------------------------------------------------------- /cvar_distributions.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/cvar_distributions.png -------------------------------------------------------------------------------- /env_visualizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/env_visualizer.py -------------------------------------------------------------------------------- /marinenav_env/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/marinenav_env/__init__.py -------------------------------------------------------------------------------- /marinenav_env/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/marinenav_env/envs/__init__.py -------------------------------------------------------------------------------- /marinenav_env/envs/marinenav_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/marinenav_env/envs/marinenav_env.py -------------------------------------------------------------------------------- /marinenav_env/envs/utils/robot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/marinenav_env/envs/utils/robot.py -------------------------------------------------------------------------------- /marinenav_env/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/marinenav_env/setup.py -------------------------------------------------------------------------------- /pretrained_models/DQN/seed_3/best_model.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/DQN/seed_3/best_model.zip -------------------------------------------------------------------------------- /pretrained_models/DQN/seed_3/evaluations.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/DQN/seed_3/evaluations.npz -------------------------------------------------------------------------------- /pretrained_models/DQN/seed_3/latest_model.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/DQN/seed_3/latest_model.zip -------------------------------------------------------------------------------- /pretrained_models/DQN/seed_3/training_schedule.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/DQN/seed_3/training_schedule.json -------------------------------------------------------------------------------- /pretrained_models/DQN/seed_3/trial_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/DQN/seed_3/trial_config.json -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/adaptive_evaluations.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/adaptive_evaluations.npz -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/constructor_params.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/constructor_params.json -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/eval_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/eval_config.json -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/greedy_evaluations.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/greedy_evaluations.npz -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/network_params.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/network_params.pth -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/training_schedule.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/training_schedule.json -------------------------------------------------------------------------------- /pretrained_models/IQN/seed_3/trial_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/pretrained_models/IQN/seed_3/trial_config.json -------------------------------------------------------------------------------- /run_experiments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/run_experiments.py -------------------------------------------------------------------------------- /scripts/plot_eval_returns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/scripts/plot_eval_returns.py -------------------------------------------------------------------------------- /scripts/visualize_IQN_eval_episode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/scripts/visualize_IQN_eval_episode.py -------------------------------------------------------------------------------- /scripts/visualize_exp_episode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/scripts/visualize_exp_episode.py -------------------------------------------------------------------------------- /system_requirements: -------------------------------------------------------------------------------- 1 | ubuntu 20.04 2 | gym 0.19.0 -------------------------------------------------------------------------------- /thirdparty/IQN/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/IQN/__init__.py -------------------------------------------------------------------------------- /thirdparty/IQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/IQN/agent.py -------------------------------------------------------------------------------- /thirdparty/IQN/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/IQN/model.py -------------------------------------------------------------------------------- /thirdparty/IQN/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/IQN/replay_buffer.py -------------------------------------------------------------------------------- /thirdparty/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ars/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ars/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ars/ars.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ars/ars.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ars/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ars/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/envs/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/envs/invalid_actions_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/envs/invalid_actions_env.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/maskable/buffers.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/maskable/callbacks.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/maskable/distributions.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/maskable/evaluation.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/maskable/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/maskable/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/maskable/utils.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/recurrent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/recurrent/buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/recurrent/buffers.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/recurrent/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/recurrent/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/recurrent/type_aliases.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/recurrent/type_aliases.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/utils.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/vec_env/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/vec_env/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/vec_env/async_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/vec_env/async_eval.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/wrappers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/wrappers/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/wrappers/action_masker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/wrappers/action_masker.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/common/wrappers/time_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/common/wrappers/time_feature.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ppo_mask/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ppo_mask/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ppo_mask/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ppo_mask/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ppo_mask/ppo_mask.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ppo_mask/ppo_mask.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ppo_recurrent/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ppo_recurrent/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ppo_recurrent/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ppo_recurrent/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/ppo_recurrent/ppo_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/ppo_recurrent/ppo_recurrent.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/py.typed: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/qrdqn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/qrdqn/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/qrdqn/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/qrdqn/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/qrdqn/qrdqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/qrdqn/qrdqn.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/tqc/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/tqc/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/tqc/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/tqc/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/tqc/tqc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/tqc/tqc.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/trpo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/trpo/__init__.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/trpo/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/trpo/policies.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/trpo/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/sb3_contrib/trpo/trpo.py -------------------------------------------------------------------------------- /thirdparty/sb3_contrib/version.txt: -------------------------------------------------------------------------------- 1 | 1.7.0a10 2 | -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/a2c/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/a2c/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/a2c/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/a2c/a2c.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/a2c/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/a2c/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/atari_wrappers.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/base_class.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/base_class.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/buffers.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/callbacks.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/distributions.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/env_checker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/env_checker.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/env_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/env_util.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/envs/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/envs/bit_flipping_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/envs/bit_flipping_env.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/envs/identity_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/envs/identity_env.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/envs/multi_input_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/envs/multi_input_envs.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/evaluation.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/logger.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/monitor.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/noise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/noise.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/off_policy_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/off_policy_algorithm.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/on_policy_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/on_policy_algorithm.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/preprocessing.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/results_plotter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/results_plotter.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/running_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/running_mean_std.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/save_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/save_util.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/sb2_compat/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/sb2_compat/rmsprop_tf_like.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/sb2_compat/rmsprop_tf_like.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/torch_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/torch_layers.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/type_aliases.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/type_aliases.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/utils.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/base_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/base_vec_env.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/dummy_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/dummy_vec_env.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/stacked_observations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/stacked_observations.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/subproc_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/subproc_vec_env.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/util.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_check_nan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_check_nan.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_extract_dict_obs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_extract_dict_obs.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_frame_stack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_frame_stack.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_monitor.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_normalize.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_transpose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_transpose.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/common/vec_env/vec_video_recorder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/common/vec_env/vec_video_recorder.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/ddpg/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/ddpg/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/ddpg/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/ddpg/ddpg.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/ddpg/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/ddpg/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/dqn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/dqn/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/dqn/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/dqn/dqn.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/dqn/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/dqn/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/her/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/her/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/her/goal_selection_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/her/goal_selection_strategy.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/her/her_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/her/her_replay_buffer.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/ppo/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/ppo/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/ppo/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/ppo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/ppo/ppo.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/py.typed: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/sac/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/sac/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/sac/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/sac/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/sac/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/sac/sac.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/td3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/td3/__init__.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/td3/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/td3/policies.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/td3/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/thirdparty/stable_baselines3/td3/td3.py -------------------------------------------------------------------------------- /thirdparty/stable_baselines3/version.txt: -------------------------------------------------------------------------------- 1 | 1.6.2 2 | -------------------------------------------------------------------------------- /train_IQN_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/train_IQN_model.py -------------------------------------------------------------------------------- /train_sb3_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RobustFieldAutonomyLab/Distributional_RL_Navigation/HEAD/train_sb3_model.py --------------------------------------------------------------------------------