├── README.md ├── config ├── decouple.py ├── locomotion.py ├── toy_env.py ├── toy_env_decouple.py └── toy_safe_env.py ├── cost.py ├── diffuser ├── __init__.py ├── agent │ ├── COMBOPolicy.py │ ├── CQLPolicy.py │ ├── SACPolicy.py │ └── __init__.py ├── datasets │ ├── __init__.py │ ├── buffer.py │ ├── d4rl.py │ ├── normalization.py │ ├── preprocessing.py │ ├── replaybuffer.py │ └── sequence.py ├── environments │ ├── BulletSafetyGym.py │ ├── __init__.py │ ├── ant.py │ ├── assets │ │ ├── ant.xml │ │ ├── half_cheetah.xml │ │ ├── hopper.xml │ │ └── walker2d.xml │ ├── double_pendulum.py │ ├── half_cheetah.py │ ├── hopper.py │ ├── mycliffwalking.py │ ├── myfrozen_lake.py │ ├── myroulette.py │ ├── ocpm.py │ ├── reacher.py │ ├── registration.py │ ├── single_pendulum.py │ ├── two_step_mdp.py │ ├── walker2d.py │ └── wrappers.py ├── models │ ├── TCN.py │ ├── __init__.py │ ├── diffusion.py │ ├── helpers.py │ └── temporal.py ├── sampling │ ├── __init__.py │ ├── functions.py │ ├── guides.py │ └── policies.py └── utils │ ├── __init__.py │ ├── arrays.py │ ├── cloud.py │ ├── colab.py │ ├── config.py │ ├── git_utils.py │ ├── iql.py │ ├── logger.py │ ├── progress.py │ ├── pybullet_utils.py │ ├── rendering.py │ ├── serialization.py │ ├── setup.py │ ├── timer.py │ ├── training.py │ ├── transformations.py │ └── video.py ├── environment.yml ├── scripts ├── data_generate.py ├── diffuser_sample.ipynb ├── diffuser_sample.py ├── download_pretrained.sh ├── plan_cost_guided.py ├── plan_guided.py ├── policylearning.py ├── read_results.py ├── release-run.sh ├── train.py ├── train_cost_values.py ├── train_decouple.py └── train_values.py ├── setup.py ├── test_cost.sh ├── test_cost_bsg.sh ├── test_cost_rs.sh ├── test_cost_toyenv.sh ├── train.sh └── train_values.sh /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/README.md -------------------------------------------------------------------------------- /config/decouple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/config/decouple.py -------------------------------------------------------------------------------- /config/locomotion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/config/locomotion.py -------------------------------------------------------------------------------- /config/toy_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/config/toy_env.py -------------------------------------------------------------------------------- /config/toy_env_decouple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/config/toy_env_decouple.py -------------------------------------------------------------------------------- /config/toy_safe_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/config/toy_safe_env.py -------------------------------------------------------------------------------- /cost.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/cost.py -------------------------------------------------------------------------------- /diffuser/__init__.py: -------------------------------------------------------------------------------- 1 | from . import environments -------------------------------------------------------------------------------- /diffuser/agent/COMBOPolicy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/agent/COMBOPolicy.py -------------------------------------------------------------------------------- /diffuser/agent/CQLPolicy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/agent/CQLPolicy.py -------------------------------------------------------------------------------- /diffuser/agent/SACPolicy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/agent/SACPolicy.py -------------------------------------------------------------------------------- /diffuser/agent/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/agent/__init__.py -------------------------------------------------------------------------------- /diffuser/datasets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/__init__.py -------------------------------------------------------------------------------- /diffuser/datasets/buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/buffer.py -------------------------------------------------------------------------------- /diffuser/datasets/d4rl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/d4rl.py -------------------------------------------------------------------------------- /diffuser/datasets/normalization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/normalization.py -------------------------------------------------------------------------------- /diffuser/datasets/preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/preprocessing.py -------------------------------------------------------------------------------- /diffuser/datasets/replaybuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/replaybuffer.py -------------------------------------------------------------------------------- /diffuser/datasets/sequence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/datasets/sequence.py -------------------------------------------------------------------------------- /diffuser/environments/BulletSafetyGym.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /diffuser/environments/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/__init__.py -------------------------------------------------------------------------------- /diffuser/environments/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/ant.py -------------------------------------------------------------------------------- /diffuser/environments/assets/ant.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/assets/ant.xml -------------------------------------------------------------------------------- /diffuser/environments/assets/half_cheetah.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/assets/half_cheetah.xml -------------------------------------------------------------------------------- /diffuser/environments/assets/hopper.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/assets/hopper.xml -------------------------------------------------------------------------------- /diffuser/environments/assets/walker2d.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/assets/walker2d.xml -------------------------------------------------------------------------------- /diffuser/environments/double_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/double_pendulum.py -------------------------------------------------------------------------------- /diffuser/environments/half_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/half_cheetah.py -------------------------------------------------------------------------------- /diffuser/environments/hopper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/hopper.py -------------------------------------------------------------------------------- /diffuser/environments/mycliffwalking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/mycliffwalking.py -------------------------------------------------------------------------------- /diffuser/environments/myfrozen_lake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/myfrozen_lake.py -------------------------------------------------------------------------------- /diffuser/environments/myroulette.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/myroulette.py -------------------------------------------------------------------------------- /diffuser/environments/ocpm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/ocpm.py -------------------------------------------------------------------------------- /diffuser/environments/reacher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/reacher.py -------------------------------------------------------------------------------- /diffuser/environments/registration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/registration.py -------------------------------------------------------------------------------- /diffuser/environments/single_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/single_pendulum.py -------------------------------------------------------------------------------- /diffuser/environments/two_step_mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/two_step_mdp.py -------------------------------------------------------------------------------- /diffuser/environments/walker2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/walker2d.py -------------------------------------------------------------------------------- /diffuser/environments/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/environments/wrappers.py -------------------------------------------------------------------------------- /diffuser/models/TCN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/models/TCN.py -------------------------------------------------------------------------------- /diffuser/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/models/__init__.py -------------------------------------------------------------------------------- /diffuser/models/diffusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/models/diffusion.py -------------------------------------------------------------------------------- /diffuser/models/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/models/helpers.py -------------------------------------------------------------------------------- /diffuser/models/temporal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/models/temporal.py -------------------------------------------------------------------------------- /diffuser/sampling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/sampling/__init__.py -------------------------------------------------------------------------------- /diffuser/sampling/functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/sampling/functions.py -------------------------------------------------------------------------------- /diffuser/sampling/guides.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/sampling/guides.py -------------------------------------------------------------------------------- /diffuser/sampling/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/sampling/policies.py -------------------------------------------------------------------------------- /diffuser/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/__init__.py -------------------------------------------------------------------------------- /diffuser/utils/arrays.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/arrays.py -------------------------------------------------------------------------------- /diffuser/utils/cloud.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/cloud.py -------------------------------------------------------------------------------- /diffuser/utils/colab.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/colab.py -------------------------------------------------------------------------------- /diffuser/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/config.py -------------------------------------------------------------------------------- /diffuser/utils/git_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/git_utils.py -------------------------------------------------------------------------------- /diffuser/utils/iql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/iql.py -------------------------------------------------------------------------------- /diffuser/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/logger.py -------------------------------------------------------------------------------- /diffuser/utils/progress.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/progress.py -------------------------------------------------------------------------------- /diffuser/utils/pybullet_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/pybullet_utils.py -------------------------------------------------------------------------------- /diffuser/utils/rendering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/rendering.py -------------------------------------------------------------------------------- /diffuser/utils/serialization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/serialization.py -------------------------------------------------------------------------------- /diffuser/utils/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/setup.py -------------------------------------------------------------------------------- /diffuser/utils/timer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/timer.py -------------------------------------------------------------------------------- /diffuser/utils/training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/training.py -------------------------------------------------------------------------------- /diffuser/utils/transformations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/transformations.py -------------------------------------------------------------------------------- /diffuser/utils/video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/diffuser/utils/video.py -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/environment.yml -------------------------------------------------------------------------------- /scripts/data_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/data_generate.py -------------------------------------------------------------------------------- /scripts/diffuser_sample.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/diffuser_sample.ipynb -------------------------------------------------------------------------------- /scripts/diffuser_sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/diffuser_sample.py -------------------------------------------------------------------------------- /scripts/download_pretrained.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/download_pretrained.sh -------------------------------------------------------------------------------- /scripts/plan_cost_guided.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/plan_cost_guided.py -------------------------------------------------------------------------------- /scripts/plan_guided.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/plan_guided.py -------------------------------------------------------------------------------- /scripts/policylearning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/policylearning.py -------------------------------------------------------------------------------- /scripts/read_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/read_results.py -------------------------------------------------------------------------------- /scripts/release-run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/release-run.sh -------------------------------------------------------------------------------- /scripts/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/train.py -------------------------------------------------------------------------------- /scripts/train_cost_values.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/train_cost_values.py -------------------------------------------------------------------------------- /scripts/train_decouple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/train_decouple.py -------------------------------------------------------------------------------- /scripts/train_values.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/scripts/train_values.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/setup.py -------------------------------------------------------------------------------- /test_cost.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/test_cost.sh -------------------------------------------------------------------------------- /test_cost_bsg.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/test_cost_bsg.sh -------------------------------------------------------------------------------- /test_cost_rs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/test_cost_rs.sh -------------------------------------------------------------------------------- /test_cost_toyenv.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/test_cost_toyenv.sh -------------------------------------------------------------------------------- /train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/train.sh -------------------------------------------------------------------------------- /train_values.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qianlin04/Safe-offline-RL-with-diffusion-model/HEAD/train_values.sh --------------------------------------------------------------------------------