├── L2RL-pytorch ├── envs.py ├── main.py ├── model.py ├── my_optim.py ├── test.py └── train.py ├── Meta-RL ├── A3C-Meta-Bandit.py ├── A3C-Meta-Context.py ├── A3C-Meta-Grid.py ├── gridworld.py ├── helper.py └── resources │ ├── FreeSans.ttf │ ├── bandit.png │ └── c_bandit.png ├── README.md ├── meta-rl-log.rar ├── metalearning_RL ├── generate_tasks.py ├── helper │ ├── __init__.py │ ├── algo │ │ ├── __init__.py │ │ └── ppo.py │ ├── envs │ │ ├── __init__.py │ │ ├── bandit.py │ │ ├── mdp.py │ │ ├── multiprocessing_env.py │ │ ├── navigation.py │ │ ├── normalized_env.py │ │ ├── subproc_vec_env.py │ │ └── utils.py │ ├── evaluate_model.py │ ├── metalearn.py │ ├── model_init.py │ ├── models │ │ ├── __init__.py │ │ ├── gru.py │ │ └── snail.py │ ├── policies │ │ ├── __init__.py │ │ ├── gru.py │ │ └── snail.py │ ├── sampler.py │ ├── snail_blocks.py │ └── values │ │ ├── __init__.py │ │ ├── gru.py │ │ └── snail.py ├── list_actions_in_env.py ├── logs_eval │ ├── rl2 │ │ └── reinforce_bandit_5_10_adam_lr0.005_numtasks200.pkl │ └── snail │ │ └── reinforce_bandit_5_10_adam_lr0.005_numtasks200.pkl ├── rl2_eval.py ├── rl2_eval_modified.py └── rl2_train.py └── pytorch-maml-rl ├── _assets └── halfcheetahdir.gif ├── configs └── maml │ ├── 2d-navigation.yaml │ ├── ant-dir.yaml │ ├── ant-goal.yaml │ ├── ant-vel.yaml │ ├── bandit │ ├── bandit-k10-n10.yaml │ ├── bandit-k10-n100.yaml │ ├── bandit-k10-n500.yaml │ ├── bandit-k5-n10.yaml │ ├── bandit-k5-n100.yaml │ ├── bandit-k5-n500.yaml │ ├── bandit-k50-n10.yaml │ ├── bandit-k50-n100.yaml │ └── bandit-k50-n500.yaml │ ├── halfcheetah-dir.yaml │ └── halfcheetah-vel.yaml ├── maml_rl ├── __init__.py ├── baseline.py ├── envs │ ├── __init__.py │ ├── bandit.py │ ├── mdp.py │ ├── mujoco │ │ ├── __init__.py │ │ ├── ant.py │ │ └── half_cheetah.py │ ├── navigation.py │ └── utils │ │ ├── __init__.py │ │ ├── normalized_env.py │ │ ├── sync_vector_env.py │ │ └── wrappers.py ├── episode.py ├── metalearners │ ├── __init__.py │ ├── base.py │ └── maml_trpo.py ├── policies │ ├── __init__.py │ ├── categorical_mlp.py │ ├── normal_mlp.py │ └── policy.py ├── samplers │ ├── __init__.py │ ├── multi_task_sampler.py │ └── sampler.py ├── tests │ ├── __init__.py │ ├── samplers │ │ ├── __init__.py │ │ └── test_multi_task_sampler.py │ ├── test_episode.py │ └── utils │ │ ├── __init__.py │ │ └── test_torch_utils.py └── utils │ ├── __init__.py │ ├── helpers.py │ ├── optimization.py │ ├── reinforcement_learning.py │ └── torch_utils.py ├── requirements.txt ├── test.py └── train.py /L2RL-pytorch/envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/L2RL-pytorch/envs.py -------------------------------------------------------------------------------- /L2RL-pytorch/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/L2RL-pytorch/main.py -------------------------------------------------------------------------------- /L2RL-pytorch/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/L2RL-pytorch/model.py -------------------------------------------------------------------------------- /L2RL-pytorch/my_optim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/L2RL-pytorch/my_optim.py -------------------------------------------------------------------------------- /L2RL-pytorch/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/L2RL-pytorch/test.py -------------------------------------------------------------------------------- /L2RL-pytorch/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/L2RL-pytorch/train.py -------------------------------------------------------------------------------- /Meta-RL/A3C-Meta-Bandit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/A3C-Meta-Bandit.py -------------------------------------------------------------------------------- /Meta-RL/A3C-Meta-Context.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/A3C-Meta-Context.py -------------------------------------------------------------------------------- /Meta-RL/A3C-Meta-Grid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/A3C-Meta-Grid.py -------------------------------------------------------------------------------- /Meta-RL/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/gridworld.py -------------------------------------------------------------------------------- /Meta-RL/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/helper.py -------------------------------------------------------------------------------- /Meta-RL/resources/FreeSans.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/resources/FreeSans.ttf -------------------------------------------------------------------------------- /Meta-RL/resources/bandit.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/resources/bandit.png -------------------------------------------------------------------------------- /Meta-RL/resources/c_bandit.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/Meta-RL/resources/c_bandit.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/README.md -------------------------------------------------------------------------------- /meta-rl-log.rar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/meta-rl-log.rar -------------------------------------------------------------------------------- /metalearning_RL/generate_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/generate_tasks.py -------------------------------------------------------------------------------- /metalearning_RL/helper/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/__init__.py -------------------------------------------------------------------------------- /metalearning_RL/helper/algo/__init__.py: -------------------------------------------------------------------------------- 1 | from .ppo import PPO -------------------------------------------------------------------------------- /metalearning_RL/helper/algo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/algo/ppo.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/__init__.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/bandit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/bandit.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/mdp.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/multiprocessing_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/multiprocessing_env.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/navigation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/navigation.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/normalized_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/normalized_env.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/subproc_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/subproc_vec_env.py -------------------------------------------------------------------------------- /metalearning_RL/helper/envs/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/envs/utils.py -------------------------------------------------------------------------------- /metalearning_RL/helper/evaluate_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/evaluate_model.py -------------------------------------------------------------------------------- /metalearning_RL/helper/metalearn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/metalearn.py -------------------------------------------------------------------------------- /metalearning_RL/helper/model_init.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/model_init.py -------------------------------------------------------------------------------- /metalearning_RL/helper/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/models/__init__.py -------------------------------------------------------------------------------- /metalearning_RL/helper/models/gru.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/models/gru.py -------------------------------------------------------------------------------- /metalearning_RL/helper/models/snail.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/models/snail.py -------------------------------------------------------------------------------- /metalearning_RL/helper/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/policies/__init__.py -------------------------------------------------------------------------------- /metalearning_RL/helper/policies/gru.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/policies/gru.py -------------------------------------------------------------------------------- /metalearning_RL/helper/policies/snail.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/policies/snail.py -------------------------------------------------------------------------------- /metalearning_RL/helper/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/sampler.py -------------------------------------------------------------------------------- /metalearning_RL/helper/snail_blocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/snail_blocks.py -------------------------------------------------------------------------------- /metalearning_RL/helper/values/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/values/__init__.py -------------------------------------------------------------------------------- /metalearning_RL/helper/values/gru.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/values/gru.py -------------------------------------------------------------------------------- /metalearning_RL/helper/values/snail.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/helper/values/snail.py -------------------------------------------------------------------------------- /metalearning_RL/list_actions_in_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/list_actions_in_env.py -------------------------------------------------------------------------------- /metalearning_RL/logs_eval/rl2/reinforce_bandit_5_10_adam_lr0.005_numtasks200.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/logs_eval/rl2/reinforce_bandit_5_10_adam_lr0.005_numtasks200.pkl -------------------------------------------------------------------------------- /metalearning_RL/logs_eval/snail/reinforce_bandit_5_10_adam_lr0.005_numtasks200.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/logs_eval/snail/reinforce_bandit_5_10_adam_lr0.005_numtasks200.pkl -------------------------------------------------------------------------------- /metalearning_RL/rl2_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/rl2_eval.py -------------------------------------------------------------------------------- /metalearning_RL/rl2_eval_modified.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/rl2_eval_modified.py -------------------------------------------------------------------------------- /metalearning_RL/rl2_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/metalearning_RL/rl2_train.py -------------------------------------------------------------------------------- /pytorch-maml-rl/_assets/halfcheetahdir.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/_assets/halfcheetahdir.gif -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/2d-navigation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/2d-navigation.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/ant-dir.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/ant-dir.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/ant-goal.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/ant-goal.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/ant-vel.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/ant-vel.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k10-n10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k10-n10.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k10-n100.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k10-n100.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k10-n500.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k10-n500.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k5-n10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k5-n10.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k5-n100.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k5-n100.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k5-n500.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k5-n500.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k50-n10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k50-n10.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k50-n100.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k50-n100.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/bandit/bandit-k50-n500.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/bandit/bandit-k50-n500.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/halfcheetah-dir.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/halfcheetah-dir.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/configs/maml/halfcheetah-vel.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/configs/maml/halfcheetah-vel.yaml -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/baseline.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/__init__.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/bandit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/bandit.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/mdp.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/mujoco/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/mujoco/ant.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/mujoco/half_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/mujoco/half_cheetah.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/navigation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/navigation.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/utils/normalized_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/utils/normalized_env.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/utils/sync_vector_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/utils/sync_vector_env.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/envs/utils/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/envs/utils/wrappers.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/episode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/episode.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/metalearners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/metalearners/__init__.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/metalearners/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/metalearners/base.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/metalearners/maml_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/metalearners/maml_trpo.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/policies/__init__.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/policies/categorical_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/policies/categorical_mlp.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/policies/normal_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/policies/normal_mlp.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/policies/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/policies/policy.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/samplers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/samplers/__init__.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/samplers/multi_task_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/samplers/multi_task_sampler.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/samplers/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/samplers/sampler.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/tests/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/tests/samplers/test_multi_task_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/tests/samplers/test_multi_task_sampler.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/tests/test_episode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/tests/test_episode.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/tests/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/tests/utils/__init__.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/tests/utils/test_torch_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/tests/utils/test_torch_utils.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/utils/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/utils/helpers.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/utils/optimization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/utils/optimization.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/utils/reinforcement_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/utils/reinforcement_learning.py -------------------------------------------------------------------------------- /pytorch-maml-rl/maml_rl/utils/torch_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/maml_rl/utils/torch_utils.py -------------------------------------------------------------------------------- /pytorch-maml-rl/requirements.txt: -------------------------------------------------------------------------------- 1 | torch>=1.3 2 | gym[mujoco]>=0.15 3 | tqdm>=4.0 4 | pyyaml>=5.1 -------------------------------------------------------------------------------- /pytorch-maml-rl/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/test.py -------------------------------------------------------------------------------- /pytorch-maml-rl/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucifer2859/meta-RL/HEAD/pytorch-maml-rl/train.py --------------------------------------------------------------------------------