├── README.md ├── acer ├── algos │ └── acer.py ├── main.py ├── policies │ ├── __init__.py │ ├── cnn_policy.py │ └── mlp_policy.py └── utils │ ├── buffer.py │ ├── cnn_utils.py │ ├── distributions.py │ ├── runner.py │ ├── test.py │ └── tf_utils.py ├── airl ├── discriminator │ └── discriminator.py ├── main.py └── utils │ ├── mujoco_dataset.py │ ├── replay_buffer.py │ └── runner.py ├── collect.py ├── dataset ├── mb2 │ ├── Walker2d-v2.h5 │ └── Walker2d-v2 │ │ ├── checkpoint │ │ ├── expert_replay_buffer.data-00000-of-00001 │ │ ├── expert_replay_buffer.index │ │ ├── expert_replay_buffer.meta │ │ └── policy.npy └── sac │ ├── Walker2d-v2.h5 │ └── Walker2d-v2 │ ├── checkpoint │ ├── expert_replay_buffer.data-00000-of-00001 │ ├── expert_replay_buffer.index │ ├── expert_replay_buffer.meta │ └── policy.npy ├── evaluate.py ├── gail ├── bc.py ├── discriminator │ ├── binary_classifier.py │ ├── discriminator.py │ └── linear_reward.py ├── main.py ├── utils │ ├── mujoco_dataset.py │ ├── replay_buffer.py │ └── runner.py └── visualize.py ├── lunzi ├── Logger.py ├── __init__.py ├── config.py ├── dataset.py ├── nn │ ├── __init__.py │ ├── container.py │ ├── flat_param.py │ ├── layers.py │ ├── loss.py │ ├── module.py │ ├── parameter.py │ ├── patch.py │ └── utils.py ├── stubs.py └── stubs.pyi ├── mbrl ├── bc │ └── main.py ├── gail │ ├── algos │ │ └── trpo.py │ ├── discriminator │ │ ├── binary_classifier.py │ │ └── discriminator.py │ ├── main.py │ ├── policies │ │ ├── __init__.py │ │ └── gaussian_mlp_policy.py │ ├── utils │ │ ├── replay_buffer.py │ │ └── runner.py │ └── v_function │ │ ├── __init__.py │ │ └── mlp_v_function.py └── visualize.py ├── requirement.txt ├── run_collect.sh ├── run_evaluate.sh ├── sac ├── algos │ └── sac.py ├── main.py └── policies │ ├── actor.py │ └── critic.py ├── scripts ├── run_airl.sh ├── run_bc.sh ├── run_dagger.sh ├── run_fem.sh ├── run_gail.sh ├── run_gail_regularization.sh ├── run_mbrl_bc.sh ├── run_mbrl_gail.sh ├── run_sac.sh ├── run_simplex.sh ├── run_td3.sh └── run_trpo.sh ├── trpo ├── algos │ ├── __init__.py │ └── trpo.py ├── main.py ├── policies │ ├── __init__.py │ └── gaussian_mlp_policy.py ├── utils │ ├── OU_noise.py │ ├── __init__.py │ ├── normalizer.py │ ├── np_utils.py │ ├── runner.py │ └── truncated_normal.py └── v_function │ ├── __init__.py │ └── mlp_v_function.py └── utils ├── __init__.py ├── envs ├── __init__.py ├── atari_wrapper.py ├── batched_env.py ├── monitor.py ├── mujoco │ ├── __init__.py │ ├── half_cheetah_env.py │ ├── hopper_env.py │ ├── linear_env.py │ ├── virtual_env.py │ └── walker2d_env.py └── mujoco_wrapper.py ├── flags.py ├── tf_utils.py └── timeit.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/README.md -------------------------------------------------------------------------------- /acer/algos/acer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/algos/acer.py -------------------------------------------------------------------------------- /acer/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/main.py -------------------------------------------------------------------------------- /acer/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/policies/__init__.py -------------------------------------------------------------------------------- /acer/policies/cnn_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/policies/cnn_policy.py -------------------------------------------------------------------------------- /acer/policies/mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/policies/mlp_policy.py -------------------------------------------------------------------------------- /acer/utils/buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/utils/buffer.py -------------------------------------------------------------------------------- /acer/utils/cnn_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/utils/cnn_utils.py -------------------------------------------------------------------------------- /acer/utils/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/utils/distributions.py -------------------------------------------------------------------------------- /acer/utils/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/utils/runner.py -------------------------------------------------------------------------------- /acer/utils/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/utils/test.py -------------------------------------------------------------------------------- /acer/utils/tf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/acer/utils/tf_utils.py -------------------------------------------------------------------------------- /airl/discriminator/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/airl/discriminator/discriminator.py -------------------------------------------------------------------------------- /airl/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/airl/main.py -------------------------------------------------------------------------------- /airl/utils/mujoco_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/airl/utils/mujoco_dataset.py -------------------------------------------------------------------------------- /airl/utils/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/airl/utils/replay_buffer.py -------------------------------------------------------------------------------- /airl/utils/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/airl/utils/runner.py -------------------------------------------------------------------------------- /collect.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/collect.py -------------------------------------------------------------------------------- /dataset/mb2/Walker2d-v2.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/mb2/Walker2d-v2.h5 -------------------------------------------------------------------------------- /dataset/mb2/Walker2d-v2/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/mb2/Walker2d-v2/checkpoint -------------------------------------------------------------------------------- /dataset/mb2/Walker2d-v2/expert_replay_buffer.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/mb2/Walker2d-v2/expert_replay_buffer.data-00000-of-00001 -------------------------------------------------------------------------------- /dataset/mb2/Walker2d-v2/expert_replay_buffer.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/mb2/Walker2d-v2/expert_replay_buffer.index -------------------------------------------------------------------------------- /dataset/mb2/Walker2d-v2/expert_replay_buffer.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/mb2/Walker2d-v2/expert_replay_buffer.meta -------------------------------------------------------------------------------- /dataset/mb2/Walker2d-v2/policy.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/mb2/Walker2d-v2/policy.npy -------------------------------------------------------------------------------- /dataset/sac/Walker2d-v2.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/sac/Walker2d-v2.h5 -------------------------------------------------------------------------------- /dataset/sac/Walker2d-v2/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/sac/Walker2d-v2/checkpoint -------------------------------------------------------------------------------- /dataset/sac/Walker2d-v2/expert_replay_buffer.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/sac/Walker2d-v2/expert_replay_buffer.data-00000-of-00001 -------------------------------------------------------------------------------- /dataset/sac/Walker2d-v2/expert_replay_buffer.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/sac/Walker2d-v2/expert_replay_buffer.index -------------------------------------------------------------------------------- /dataset/sac/Walker2d-v2/expert_replay_buffer.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/sac/Walker2d-v2/expert_replay_buffer.meta -------------------------------------------------------------------------------- /dataset/sac/Walker2d-v2/policy.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/dataset/sac/Walker2d-v2/policy.npy -------------------------------------------------------------------------------- /evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/evaluate.py -------------------------------------------------------------------------------- /gail/bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/bc.py -------------------------------------------------------------------------------- /gail/discriminator/binary_classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/discriminator/binary_classifier.py -------------------------------------------------------------------------------- /gail/discriminator/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/discriminator/discriminator.py -------------------------------------------------------------------------------- /gail/discriminator/linear_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/discriminator/linear_reward.py -------------------------------------------------------------------------------- /gail/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/main.py -------------------------------------------------------------------------------- /gail/utils/mujoco_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/utils/mujoco_dataset.py -------------------------------------------------------------------------------- /gail/utils/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/utils/replay_buffer.py -------------------------------------------------------------------------------- /gail/utils/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/utils/runner.py -------------------------------------------------------------------------------- /gail/visualize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/gail/visualize.py -------------------------------------------------------------------------------- /lunzi/Logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/Logger.py -------------------------------------------------------------------------------- /lunzi/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/__init__.py -------------------------------------------------------------------------------- /lunzi/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/config.py -------------------------------------------------------------------------------- /lunzi/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/dataset.py -------------------------------------------------------------------------------- /lunzi/nn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/__init__.py -------------------------------------------------------------------------------- /lunzi/nn/container.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/container.py -------------------------------------------------------------------------------- /lunzi/nn/flat_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/flat_param.py -------------------------------------------------------------------------------- /lunzi/nn/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/layers.py -------------------------------------------------------------------------------- /lunzi/nn/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/loss.py -------------------------------------------------------------------------------- /lunzi/nn/module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/module.py -------------------------------------------------------------------------------- /lunzi/nn/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/parameter.py -------------------------------------------------------------------------------- /lunzi/nn/patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/patch.py -------------------------------------------------------------------------------- /lunzi/nn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/nn/utils.py -------------------------------------------------------------------------------- /lunzi/stubs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/stubs.py -------------------------------------------------------------------------------- /lunzi/stubs.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/lunzi/stubs.pyi -------------------------------------------------------------------------------- /mbrl/bc/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/bc/main.py -------------------------------------------------------------------------------- /mbrl/gail/algos/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/algos/trpo.py -------------------------------------------------------------------------------- /mbrl/gail/discriminator/binary_classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/discriminator/binary_classifier.py -------------------------------------------------------------------------------- /mbrl/gail/discriminator/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/discriminator/discriminator.py -------------------------------------------------------------------------------- /mbrl/gail/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/main.py -------------------------------------------------------------------------------- /mbrl/gail/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/policies/__init__.py -------------------------------------------------------------------------------- /mbrl/gail/policies/gaussian_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/policies/gaussian_mlp_policy.py -------------------------------------------------------------------------------- /mbrl/gail/utils/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/utils/replay_buffer.py -------------------------------------------------------------------------------- /mbrl/gail/utils/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/utils/runner.py -------------------------------------------------------------------------------- /mbrl/gail/v_function/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/v_function/__init__.py -------------------------------------------------------------------------------- /mbrl/gail/v_function/mlp_v_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/gail/v_function/mlp_v_function.py -------------------------------------------------------------------------------- /mbrl/visualize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/mbrl/visualize.py -------------------------------------------------------------------------------- /requirement.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/requirement.txt -------------------------------------------------------------------------------- /run_collect.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/run_collect.sh -------------------------------------------------------------------------------- /run_evaluate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/run_evaluate.sh -------------------------------------------------------------------------------- /sac/algos/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/sac/algos/sac.py -------------------------------------------------------------------------------- /sac/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/sac/main.py -------------------------------------------------------------------------------- /sac/policies/actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/sac/policies/actor.py -------------------------------------------------------------------------------- /sac/policies/critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/sac/policies/critic.py -------------------------------------------------------------------------------- /scripts/run_airl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_airl.sh -------------------------------------------------------------------------------- /scripts/run_bc.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_bc.sh -------------------------------------------------------------------------------- /scripts/run_dagger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_dagger.sh -------------------------------------------------------------------------------- /scripts/run_fem.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_fem.sh -------------------------------------------------------------------------------- /scripts/run_gail.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_gail.sh -------------------------------------------------------------------------------- /scripts/run_gail_regularization.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_gail_regularization.sh -------------------------------------------------------------------------------- /scripts/run_mbrl_bc.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_mbrl_bc.sh -------------------------------------------------------------------------------- /scripts/run_mbrl_gail.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_mbrl_gail.sh -------------------------------------------------------------------------------- /scripts/run_sac.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_sac.sh -------------------------------------------------------------------------------- /scripts/run_simplex.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_simplex.sh -------------------------------------------------------------------------------- /scripts/run_td3.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_td3.sh -------------------------------------------------------------------------------- /scripts/run_trpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/scripts/run_trpo.sh -------------------------------------------------------------------------------- /trpo/algos/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /trpo/algos/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/algos/trpo.py -------------------------------------------------------------------------------- /trpo/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/main.py -------------------------------------------------------------------------------- /trpo/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/policies/__init__.py -------------------------------------------------------------------------------- /trpo/policies/gaussian_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/policies/gaussian_mlp_policy.py -------------------------------------------------------------------------------- /trpo/utils/OU_noise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/utils/OU_noise.py -------------------------------------------------------------------------------- /trpo/utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /trpo/utils/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/utils/normalizer.py -------------------------------------------------------------------------------- /trpo/utils/np_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/utils/np_utils.py -------------------------------------------------------------------------------- /trpo/utils/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/utils/runner.py -------------------------------------------------------------------------------- /trpo/utils/truncated_normal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/utils/truncated_normal.py -------------------------------------------------------------------------------- /trpo/v_function/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/v_function/__init__.py -------------------------------------------------------------------------------- /trpo/v_function/mlp_v_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/trpo/v_function/mlp_v_function.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/__init__.py -------------------------------------------------------------------------------- /utils/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/__init__.py -------------------------------------------------------------------------------- /utils/envs/atari_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/atari_wrapper.py -------------------------------------------------------------------------------- /utils/envs/batched_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/batched_env.py -------------------------------------------------------------------------------- /utils/envs/monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/monitor.py -------------------------------------------------------------------------------- /utils/envs/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/envs/mujoco/half_cheetah_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/mujoco/half_cheetah_env.py -------------------------------------------------------------------------------- /utils/envs/mujoco/hopper_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/mujoco/hopper_env.py -------------------------------------------------------------------------------- /utils/envs/mujoco/linear_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/mujoco/linear_env.py -------------------------------------------------------------------------------- /utils/envs/mujoco/virtual_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/mujoco/virtual_env.py -------------------------------------------------------------------------------- /utils/envs/mujoco/walker2d_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/mujoco/walker2d_env.py -------------------------------------------------------------------------------- /utils/envs/mujoco_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/envs/mujoco_wrapper.py -------------------------------------------------------------------------------- /utils/flags.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/flags.py -------------------------------------------------------------------------------- /utils/tf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/tf_utils.py -------------------------------------------------------------------------------- /utils/timeit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianxusky/Code-for-Error-Bounds-of-Imitating-Policies-and-Environments/HEAD/utils/timeit.py --------------------------------------------------------------------------------