├── .gitignore ├── .python-version ├── LICENSE ├── README.md ├── examples ├── meta_learning │ ├── maml_trpo_ml1.py │ ├── maml_trpo_ml10.py │ ├── maml_trpo_ml10_v1.py │ ├── maml_trpo_ml1_v1.py │ ├── maml_trpo_ml25.py │ ├── maml_trpo_ml45.py │ ├── maml_trpo_ml45_v1.py │ ├── rl2_ml1.py │ ├── rl2_ml10.py │ ├── rl2_ml10_v1.py │ ├── rl2_ml1_v1.py │ ├── rl2_ml25.py │ ├── rl2_ml45.py │ └── rl2_ml45_v1.py └── multi_task │ ├── moore_mt10.py │ ├── mtmhsac_mt10.py │ ├── mtmhsac_mt10_v1.py │ ├── mtsac_mt10.py │ ├── paco_mt10.py │ ├── pcgrad_mt10.py │ ├── pcgrad_mt10_v1.py │ ├── ppo_mt10.py │ ├── ppo_mt25.py │ ├── ppo_mt50.py │ ├── sac_mt10.py │ └── softmodules_mt10.py ├── metaworld_algorithms ├── __init__.py ├── checkpoint.py ├── config │ ├── __init__.py │ ├── envs.py │ ├── networks.py │ ├── nn.py │ ├── optim.py │ ├── rl.py │ └── utils.py ├── envs │ ├── __init__.py │ └── metaworld.py ├── monitoring │ ├── __init__.py │ └── utils.py ├── nn │ ├── __init__.py │ ├── base.py │ ├── care.py │ ├── distributions.py │ ├── film.py │ ├── initializers.py │ ├── moore.py │ ├── multi_head.py │ ├── paco.py │ ├── regularizers.py │ ├── soft_modules.py │ └── utils.py ├── optim │ ├── __init__.py │ ├── dummy.py │ ├── gradnorm.py │ └── pcgrad.py ├── rl │ ├── __init__.py │ ├── algorithms │ │ ├── __init__.py │ │ ├── base.py │ │ ├── mamltrpo.py │ │ ├── mtsac.py │ │ ├── ppo.py │ │ ├── rl2.py │ │ ├── sac.py │ │ └── utils.py │ ├── buffers.py │ └── networks.py ├── run.py └── types.py ├── pyproject.toml ├── tests ├── conftest.py ├── data │ └── rollouts_0 │ │ ├── advantages.npy │ │ ├── dones.npy │ │ ├── observations.npy │ │ ├── returns.npy │ │ ├── rewards.npy │ │ └── values.npy ├── metaworld_algorithms │ ├── envs │ │ └── test_metaworld.py │ └── rl │ │ ├── test_networks.py │ │ └── test_utils.py └── test_tacit_assumptions.py └── uv.lock /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/.gitignore -------------------------------------------------------------------------------- /.python-version: -------------------------------------------------------------------------------- 1 | 3.12 2 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/README.md -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml1.py -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml10.py -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml10_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml10_v1.py -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml1_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml1_v1.py -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml25.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml25.py -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml45.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml45.py -------------------------------------------------------------------------------- /examples/meta_learning/maml_trpo_ml45_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/maml_trpo_ml45_v1.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml1.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml10.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml10_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml10_v1.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml1_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml1_v1.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml25.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml25.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml45.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml45.py -------------------------------------------------------------------------------- /examples/meta_learning/rl2_ml45_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/meta_learning/rl2_ml45_v1.py -------------------------------------------------------------------------------- /examples/multi_task/moore_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/moore_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/mtmhsac_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/mtmhsac_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/mtmhsac_mt10_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/mtmhsac_mt10_v1.py -------------------------------------------------------------------------------- /examples/multi_task/mtsac_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/mtsac_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/paco_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/paco_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/pcgrad_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/pcgrad_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/pcgrad_mt10_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/pcgrad_mt10_v1.py -------------------------------------------------------------------------------- /examples/multi_task/ppo_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/ppo_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/ppo_mt25.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/ppo_mt25.py -------------------------------------------------------------------------------- /examples/multi_task/ppo_mt50.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/ppo_mt50.py -------------------------------------------------------------------------------- /examples/multi_task/sac_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/sac_mt10.py -------------------------------------------------------------------------------- /examples/multi_task/softmodules_mt10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/examples/multi_task/softmodules_mt10.py -------------------------------------------------------------------------------- /metaworld_algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metaworld_algorithms/checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/checkpoint.py -------------------------------------------------------------------------------- /metaworld_algorithms/config/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metaworld_algorithms/config/envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/config/envs.py -------------------------------------------------------------------------------- /metaworld_algorithms/config/networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/config/networks.py -------------------------------------------------------------------------------- /metaworld_algorithms/config/nn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/config/nn.py -------------------------------------------------------------------------------- /metaworld_algorithms/config/optim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/config/optim.py -------------------------------------------------------------------------------- /metaworld_algorithms/config/rl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/config/rl.py -------------------------------------------------------------------------------- /metaworld_algorithms/config/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/config/utils.py -------------------------------------------------------------------------------- /metaworld_algorithms/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/envs/__init__.py -------------------------------------------------------------------------------- /metaworld_algorithms/envs/metaworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/envs/metaworld.py -------------------------------------------------------------------------------- /metaworld_algorithms/monitoring/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metaworld_algorithms/monitoring/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/monitoring/utils.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/__init__.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/base.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/care.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/care.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/distributions.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/film.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/film.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/initializers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/initializers.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/moore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/moore.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/multi_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/multi_head.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/paco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/paco.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/regularizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/regularizers.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/soft_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/soft_modules.py -------------------------------------------------------------------------------- /metaworld_algorithms/nn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/nn/utils.py -------------------------------------------------------------------------------- /metaworld_algorithms/optim/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metaworld_algorithms/optim/dummy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/optim/dummy.py -------------------------------------------------------------------------------- /metaworld_algorithms/optim/gradnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/optim/gradnorm.py -------------------------------------------------------------------------------- /metaworld_algorithms/optim/pcgrad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/optim/pcgrad.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/__init__.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/base.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/mamltrpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/mamltrpo.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/mtsac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/mtsac.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/ppo.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/rl2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/rl2.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/sac.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/algorithms/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/algorithms/utils.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/buffers.py -------------------------------------------------------------------------------- /metaworld_algorithms/rl/networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/rl/networks.py -------------------------------------------------------------------------------- /metaworld_algorithms/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/run.py -------------------------------------------------------------------------------- /metaworld_algorithms/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/metaworld_algorithms/types.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/pyproject.toml -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/data/rollouts_0/advantages.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/data/rollouts_0/advantages.npy -------------------------------------------------------------------------------- /tests/data/rollouts_0/dones.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/data/rollouts_0/dones.npy -------------------------------------------------------------------------------- /tests/data/rollouts_0/observations.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/data/rollouts_0/observations.npy -------------------------------------------------------------------------------- /tests/data/rollouts_0/returns.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/data/rollouts_0/returns.npy -------------------------------------------------------------------------------- /tests/data/rollouts_0/rewards.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/data/rollouts_0/rewards.npy -------------------------------------------------------------------------------- /tests/data/rollouts_0/values.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/data/rollouts_0/values.npy -------------------------------------------------------------------------------- /tests/metaworld_algorithms/envs/test_metaworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/metaworld_algorithms/envs/test_metaworld.py -------------------------------------------------------------------------------- /tests/metaworld_algorithms/rl/test_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/metaworld_algorithms/rl/test_networks.py -------------------------------------------------------------------------------- /tests/metaworld_algorithms/rl/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/metaworld_algorithms/rl/test_utils.py -------------------------------------------------------------------------------- /tests/test_tacit_assumptions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/tests/test_tacit_assumptions.py -------------------------------------------------------------------------------- /uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rainx0r/metaworld-algorithms/HEAD/uv.lock --------------------------------------------------------------------------------