├── .gitignore ├── Readme.md ├── ckpts ├── Swing-init_h.pt ├── Swing-init_models.pt └── Swing-init_policy.pt ├── configs ├── Swing-train_h.json5 └── Swing-train_policy.json5 ├── lunzi ├── README.md ├── __init__.py ├── _timer.py ├── file_storage.py ├── flags.py ├── initialize.py ├── notebook │ ├── __init__.py │ ├── database.py │ ├── plot.py │ └── task.py ├── requirements.txt └── utils.py ├── requirements.txt ├── rlz ├── __init__.py ├── algos │ ├── __init__.py │ ├── fast_sac.py │ ├── layers.py │ ├── sac.py │ ├── td3.py │ └── utils.py ├── dataset.py ├── distributions.py ├── dyn_model │ ├── __init__.py │ ├── base_dyn_model.py │ ├── probabilistic_model.py │ └── vec_env_from_dyn_model.py ├── multi_layer_perception.py ├── policy.py ├── qfn.py ├── replay_buffer.py ├── runner.py ├── sampler.py ├── torch_utils.py ├── trainer.py ├── utils.py ├── vfn.py └── wrappers │ ├── __init__.py │ ├── cast_dtype.py │ ├── multi_discrete_to_discrete.py │ ├── normalize_and_permute.py │ ├── quantize_action.py │ └── rescale_action.py ├── run ├── main.py ├── mf_td3.py └── read_log.py └── safe ├── __init__.py ├── ensemble.py ├── envs ├── __init__.py ├── classic_pendulum.py ├── inverted_pendulum.py └── safe_env_spec.py ├── models.py ├── normalizer.py ├── safe_sac2.py ├── simple_trainer.py ├── transition_model.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/.gitignore -------------------------------------------------------------------------------- /Readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/Readme.md -------------------------------------------------------------------------------- /ckpts/Swing-init_h.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/ckpts/Swing-init_h.pt -------------------------------------------------------------------------------- /ckpts/Swing-init_models.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/ckpts/Swing-init_models.pt -------------------------------------------------------------------------------- /ckpts/Swing-init_policy.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/ckpts/Swing-init_policy.pt -------------------------------------------------------------------------------- /configs/Swing-train_h.json5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/configs/Swing-train_h.json5 -------------------------------------------------------------------------------- /configs/Swing-train_policy.json5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/configs/Swing-train_policy.json5 -------------------------------------------------------------------------------- /lunzi/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/README.md -------------------------------------------------------------------------------- /lunzi/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/__init__.py -------------------------------------------------------------------------------- /lunzi/_timer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/_timer.py -------------------------------------------------------------------------------- /lunzi/file_storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/file_storage.py -------------------------------------------------------------------------------- /lunzi/flags.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/flags.py -------------------------------------------------------------------------------- /lunzi/initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/initialize.py -------------------------------------------------------------------------------- /lunzi/notebook/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/notebook/__init__.py -------------------------------------------------------------------------------- /lunzi/notebook/database.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/notebook/database.py -------------------------------------------------------------------------------- /lunzi/notebook/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/notebook/plot.py -------------------------------------------------------------------------------- /lunzi/notebook/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/notebook/task.py -------------------------------------------------------------------------------- /lunzi/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/requirements.txt -------------------------------------------------------------------------------- /lunzi/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/lunzi/utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/requirements.txt -------------------------------------------------------------------------------- /rlz/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/__init__.py -------------------------------------------------------------------------------- /rlz/algos/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/algos/__init__.py -------------------------------------------------------------------------------- /rlz/algos/fast_sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/algos/fast_sac.py -------------------------------------------------------------------------------- /rlz/algos/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/algos/layers.py -------------------------------------------------------------------------------- /rlz/algos/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/algos/sac.py -------------------------------------------------------------------------------- /rlz/algos/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/algos/td3.py -------------------------------------------------------------------------------- /rlz/algos/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/algos/utils.py -------------------------------------------------------------------------------- /rlz/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/dataset.py -------------------------------------------------------------------------------- /rlz/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/distributions.py -------------------------------------------------------------------------------- /rlz/dyn_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/dyn_model/__init__.py -------------------------------------------------------------------------------- /rlz/dyn_model/base_dyn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/dyn_model/base_dyn_model.py -------------------------------------------------------------------------------- /rlz/dyn_model/probabilistic_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/dyn_model/probabilistic_model.py -------------------------------------------------------------------------------- /rlz/dyn_model/vec_env_from_dyn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/dyn_model/vec_env_from_dyn_model.py -------------------------------------------------------------------------------- /rlz/multi_layer_perception.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/multi_layer_perception.py -------------------------------------------------------------------------------- /rlz/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/policy.py -------------------------------------------------------------------------------- /rlz/qfn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/qfn.py -------------------------------------------------------------------------------- /rlz/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/replay_buffer.py -------------------------------------------------------------------------------- /rlz/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/runner.py -------------------------------------------------------------------------------- /rlz/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/sampler.py -------------------------------------------------------------------------------- /rlz/torch_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/torch_utils.py -------------------------------------------------------------------------------- /rlz/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/trainer.py -------------------------------------------------------------------------------- /rlz/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/utils.py -------------------------------------------------------------------------------- /rlz/vfn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/vfn.py -------------------------------------------------------------------------------- /rlz/wrappers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/wrappers/__init__.py -------------------------------------------------------------------------------- /rlz/wrappers/cast_dtype.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/wrappers/cast_dtype.py -------------------------------------------------------------------------------- /rlz/wrappers/multi_discrete_to_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/wrappers/multi_discrete_to_discrete.py -------------------------------------------------------------------------------- /rlz/wrappers/normalize_and_permute.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/wrappers/normalize_and_permute.py -------------------------------------------------------------------------------- /rlz/wrappers/quantize_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/wrappers/quantize_action.py -------------------------------------------------------------------------------- /rlz/wrappers/rescale_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/rlz/wrappers/rescale_action.py -------------------------------------------------------------------------------- /run/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/run/main.py -------------------------------------------------------------------------------- /run/mf_td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/run/mf_td3.py -------------------------------------------------------------------------------- /run/read_log.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/run/read_log.py -------------------------------------------------------------------------------- /safe/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/__init__.py -------------------------------------------------------------------------------- /safe/ensemble.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/ensemble.py -------------------------------------------------------------------------------- /safe/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/envs/__init__.py -------------------------------------------------------------------------------- /safe/envs/classic_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/envs/classic_pendulum.py -------------------------------------------------------------------------------- /safe/envs/inverted_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/envs/inverted_pendulum.py -------------------------------------------------------------------------------- /safe/envs/safe_env_spec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/envs/safe_env_spec.py -------------------------------------------------------------------------------- /safe/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/models.py -------------------------------------------------------------------------------- /safe/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/normalizer.py -------------------------------------------------------------------------------- /safe/safe_sac2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/safe_sac2.py -------------------------------------------------------------------------------- /safe/simple_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/simple_trainer.py -------------------------------------------------------------------------------- /safe/transition_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/transition_model.py -------------------------------------------------------------------------------- /safe/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/crabs/HEAD/safe/utils.py --------------------------------------------------------------------------------