├── LICENSE ├── README.md ├── _config.yml ├── envs ├── __pycache__ │ ├── pyglet_rendering.cpython-38.pyc │ ├── simulated_cars_env.cpython-38.pyc │ ├── unicycle_env.cpython-38.pyc │ └── utils.cpython-38.pyc ├── pyglet_rendering.py ├── simulated_cars_env.py ├── unicycle_env.py └── utils.py ├── main.py ├── output ├── Unicycle-run1 │ ├── actor.pkl │ ├── critic.pkl │ ├── gp_models.pkl │ ├── gp_models_train_x.pkl │ └── gp_models_train_y.pkl ├── Unicycle-run2 │ ├── actor.pkl │ ├── comp_actor.pkl │ ├── critic.pkl │ ├── gp_models.pkl │ ├── gp_models_train_x.pkl │ └── gp_models_train_y.pkl └── Unicycle-run3 │ ├── actor.pkl │ ├── critic.pkl │ ├── gp_models.pkl │ ├── gp_models_train_x.pkl │ └── gp_models_train_y.pkl ├── rcbf_sac ├── __pycache__ │ ├── compensator.cpython-38.pyc │ ├── diff_cbf_qp.cpython-38.pyc │ ├── dynamics.cpython-38.pyc │ ├── evaluator.cpython-38.pyc │ ├── generate_rollouts.cpython-38.pyc │ ├── gp_model.cpython-38.pyc │ ├── model.cpython-38.pyc │ ├── replay_memory.cpython-38.pyc │ ├── sac_cbf.cpython-38.pyc │ └── utils.cpython-38.pyc ├── cbf_qp.py ├── compensator.py ├── diff_cbf_qp.py ├── dynamics.py ├── evaluator.py ├── generate_rollouts.py ├── gp_model.py ├── model.py ├── replay_memory.py ├── sac_cbf.py └── utils.py └── requirements.txt /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/README.md -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/_config.yml -------------------------------------------------------------------------------- /envs/__pycache__/pyglet_rendering.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/__pycache__/pyglet_rendering.cpython-38.pyc -------------------------------------------------------------------------------- /envs/__pycache__/simulated_cars_env.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/__pycache__/simulated_cars_env.cpython-38.pyc -------------------------------------------------------------------------------- /envs/__pycache__/unicycle_env.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/__pycache__/unicycle_env.cpython-38.pyc -------------------------------------------------------------------------------- /envs/__pycache__/utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/__pycache__/utils.cpython-38.pyc -------------------------------------------------------------------------------- /envs/pyglet_rendering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/pyglet_rendering.py -------------------------------------------------------------------------------- /envs/simulated_cars_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/simulated_cars_env.py -------------------------------------------------------------------------------- /envs/unicycle_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/unicycle_env.py -------------------------------------------------------------------------------- /envs/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/envs/utils.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/main.py -------------------------------------------------------------------------------- /output/Unicycle-run1/actor.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run1/actor.pkl -------------------------------------------------------------------------------- /output/Unicycle-run1/critic.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run1/critic.pkl -------------------------------------------------------------------------------- /output/Unicycle-run1/gp_models.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run1/gp_models.pkl -------------------------------------------------------------------------------- /output/Unicycle-run1/gp_models_train_x.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run1/gp_models_train_x.pkl -------------------------------------------------------------------------------- /output/Unicycle-run1/gp_models_train_y.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run1/gp_models_train_y.pkl -------------------------------------------------------------------------------- /output/Unicycle-run2/actor.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run2/actor.pkl -------------------------------------------------------------------------------- /output/Unicycle-run2/comp_actor.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run2/comp_actor.pkl -------------------------------------------------------------------------------- /output/Unicycle-run2/critic.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run2/critic.pkl -------------------------------------------------------------------------------- /output/Unicycle-run2/gp_models.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run2/gp_models.pkl -------------------------------------------------------------------------------- /output/Unicycle-run2/gp_models_train_x.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run2/gp_models_train_x.pkl -------------------------------------------------------------------------------- /output/Unicycle-run2/gp_models_train_y.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run2/gp_models_train_y.pkl -------------------------------------------------------------------------------- /output/Unicycle-run3/actor.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run3/actor.pkl -------------------------------------------------------------------------------- /output/Unicycle-run3/critic.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run3/critic.pkl -------------------------------------------------------------------------------- /output/Unicycle-run3/gp_models.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run3/gp_models.pkl -------------------------------------------------------------------------------- /output/Unicycle-run3/gp_models_train_x.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run3/gp_models_train_x.pkl -------------------------------------------------------------------------------- /output/Unicycle-run3/gp_models_train_y.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/output/Unicycle-run3/gp_models_train_y.pkl -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/compensator.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/compensator.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/diff_cbf_qp.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/diff_cbf_qp.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/dynamics.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/dynamics.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/evaluator.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/evaluator.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/generate_rollouts.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/generate_rollouts.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/gp_model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/gp_model.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/model.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/replay_memory.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/replay_memory.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/sac_cbf.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/sac_cbf.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/__pycache__/utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/__pycache__/utils.cpython-38.pyc -------------------------------------------------------------------------------- /rcbf_sac/cbf_qp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/cbf_qp.py -------------------------------------------------------------------------------- /rcbf_sac/compensator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/compensator.py -------------------------------------------------------------------------------- /rcbf_sac/diff_cbf_qp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/diff_cbf_qp.py -------------------------------------------------------------------------------- /rcbf_sac/dynamics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/dynamics.py -------------------------------------------------------------------------------- /rcbf_sac/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/evaluator.py -------------------------------------------------------------------------------- /rcbf_sac/generate_rollouts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/generate_rollouts.py -------------------------------------------------------------------------------- /rcbf_sac/gp_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/gp_model.py -------------------------------------------------------------------------------- /rcbf_sac/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/model.py -------------------------------------------------------------------------------- /rcbf_sac/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/replay_memory.py -------------------------------------------------------------------------------- /rcbf_sac/sac_cbf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/sac_cbf.py -------------------------------------------------------------------------------- /rcbf_sac/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/rcbf_sac/utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tayalmanan28/Safe_Reinforcement_Learning/HEAD/requirements.txt --------------------------------------------------------------------------------