├── .gitignore ├── LICENSE ├── README.md ├── __init__.py ├── config ├── cartpole-move.json ├── point-robot.json ├── quadrotor.json ├── tracking-double_lane.json └── tracking-sine.json ├── main.py ├── requirements.txt ├── run-ablation-1_quadrotor.sh ├── run-tracking.sh ├── run.sh └── src ├── __init__.py ├── checkpoint.py ├── cli.py ├── config.py ├── defaults.py ├── dynamics.py ├── env ├── __init__.py ├── ant_no_bonus.py ├── batch.py ├── cheetah_no_flip.py ├── half_cheetah.py ├── hopper.py ├── hopper_no_bonus.py ├── humanoid_no_bonus.py ├── mujoco_wrapper.py ├── point_robot.py ├── poles │ ├── __init__.py │ ├── classic_pendulum.py │ ├── constraints.py │ └── inverted_pendulum.py ├── quadrotor │ ├── __init__.py │ ├── constrained_tracking_eval.yaml │ ├── constrained_tracking_reset.yaml │ └── quadrotor.py ├── torch_wrapper.py ├── tracking │ ├── __init__.py │ ├── pyth_base_data.py │ ├── pyth_base_model.py │ ├── pyth_veh3dofconti_data.py │ ├── pyth_veh3dofconti_model.py │ ├── pyth_veh3dofconti_surrcstr_data.py │ ├── pyth_veh3dofconti_surrcstr_data4mpc.py │ ├── pyth_veh3dofconti_surrcstr_model.py │ └── resources │ │ ├── __init__.py │ │ ├── ref_traj_data.py │ │ └── ref_traj_model.py └── util.py ├── log.py ├── normalization.py ├── offline ├── buffer_name_converter.py └── policy_collector.py ├── policy.py ├── resources └── arial.ttf ├── sampling.py ├── shared.py ├── smbpo.py ├── squashed_gaussian.py ├── ssac.py ├── tester.py ├── torch_util.py ├── train.py ├── util.py ├── viz_cartpole ├── viz_multiplier_cartpole.py └── viz_region_cartpole.py ├── viz_curves.ipynb ├── viz_quadrotor ├── traj.png ├── viz_multiplier.py ├── viz_region.py └── viz_trj.py └── viz_tracking ├── mpc_test_and_viz.ipynb ├── opt_controller.py └── test_and_viz.ipynb /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/README.md -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /config/cartpole-move.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/config/cartpole-move.json -------------------------------------------------------------------------------- /config/point-robot.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/config/point-robot.json -------------------------------------------------------------------------------- /config/quadrotor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/config/quadrotor.json -------------------------------------------------------------------------------- /config/tracking-double_lane.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/config/tracking-double_lane.json -------------------------------------------------------------------------------- /config/tracking-sine.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/config/tracking-sine.json -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/main.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/requirements.txt -------------------------------------------------------------------------------- /run-ablation-1_quadrotor.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/run-ablation-1_quadrotor.sh -------------------------------------------------------------------------------- /run-tracking.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/run-tracking.sh -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/run.sh -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/checkpoint.py -------------------------------------------------------------------------------- /src/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/cli.py -------------------------------------------------------------------------------- /src/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/config.py -------------------------------------------------------------------------------- /src/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/defaults.py -------------------------------------------------------------------------------- /src/dynamics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/dynamics.py -------------------------------------------------------------------------------- /src/env/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/env/ant_no_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/ant_no_bonus.py -------------------------------------------------------------------------------- /src/env/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/batch.py -------------------------------------------------------------------------------- /src/env/cheetah_no_flip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/cheetah_no_flip.py -------------------------------------------------------------------------------- /src/env/half_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/half_cheetah.py -------------------------------------------------------------------------------- /src/env/hopper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/hopper.py -------------------------------------------------------------------------------- /src/env/hopper_no_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/hopper_no_bonus.py -------------------------------------------------------------------------------- /src/env/humanoid_no_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/humanoid_no_bonus.py -------------------------------------------------------------------------------- /src/env/mujoco_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/mujoco_wrapper.py -------------------------------------------------------------------------------- /src/env/point_robot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/point_robot.py -------------------------------------------------------------------------------- /src/env/poles/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/env/poles/classic_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/poles/classic_pendulum.py -------------------------------------------------------------------------------- /src/env/poles/constraints.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/poles/constraints.py -------------------------------------------------------------------------------- /src/env/poles/inverted_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/poles/inverted_pendulum.py -------------------------------------------------------------------------------- /src/env/quadrotor/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/env/quadrotor/constrained_tracking_eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/quadrotor/constrained_tracking_eval.yaml -------------------------------------------------------------------------------- /src/env/quadrotor/constrained_tracking_reset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/quadrotor/constrained_tracking_reset.yaml -------------------------------------------------------------------------------- /src/env/quadrotor/quadrotor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/quadrotor/quadrotor.py -------------------------------------------------------------------------------- /src/env/torch_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/torch_wrapper.py -------------------------------------------------------------------------------- /src/env/tracking/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/env/tracking/pyth_base_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_base_data.py -------------------------------------------------------------------------------- /src/env/tracking/pyth_base_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_base_model.py -------------------------------------------------------------------------------- /src/env/tracking/pyth_veh3dofconti_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_veh3dofconti_data.py -------------------------------------------------------------------------------- /src/env/tracking/pyth_veh3dofconti_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_veh3dofconti_model.py -------------------------------------------------------------------------------- /src/env/tracking/pyth_veh3dofconti_surrcstr_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_veh3dofconti_surrcstr_data.py -------------------------------------------------------------------------------- /src/env/tracking/pyth_veh3dofconti_surrcstr_data4mpc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_veh3dofconti_surrcstr_data4mpc.py -------------------------------------------------------------------------------- /src/env/tracking/pyth_veh3dofconti_surrcstr_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/pyth_veh3dofconti_surrcstr_model.py -------------------------------------------------------------------------------- /src/env/tracking/resources/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/env/tracking/resources/ref_traj_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/resources/ref_traj_data.py -------------------------------------------------------------------------------- /src/env/tracking/resources/ref_traj_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/tracking/resources/ref_traj_model.py -------------------------------------------------------------------------------- /src/env/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/env/util.py -------------------------------------------------------------------------------- /src/log.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/log.py -------------------------------------------------------------------------------- /src/normalization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/normalization.py -------------------------------------------------------------------------------- /src/offline/buffer_name_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/offline/buffer_name_converter.py -------------------------------------------------------------------------------- /src/offline/policy_collector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/offline/policy_collector.py -------------------------------------------------------------------------------- /src/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/policy.py -------------------------------------------------------------------------------- /src/resources/arial.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/resources/arial.ttf -------------------------------------------------------------------------------- /src/sampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/sampling.py -------------------------------------------------------------------------------- /src/shared.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/shared.py -------------------------------------------------------------------------------- /src/smbpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/smbpo.py -------------------------------------------------------------------------------- /src/squashed_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/squashed_gaussian.py -------------------------------------------------------------------------------- /src/ssac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/ssac.py -------------------------------------------------------------------------------- /src/tester.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/tester.py -------------------------------------------------------------------------------- /src/torch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/torch_util.py -------------------------------------------------------------------------------- /src/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/train.py -------------------------------------------------------------------------------- /src/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/util.py -------------------------------------------------------------------------------- /src/viz_cartpole/viz_multiplier_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_cartpole/viz_multiplier_cartpole.py -------------------------------------------------------------------------------- /src/viz_cartpole/viz_region_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_cartpole/viz_region_cartpole.py -------------------------------------------------------------------------------- /src/viz_curves.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_curves.ipynb -------------------------------------------------------------------------------- /src/viz_quadrotor/traj.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_quadrotor/traj.png -------------------------------------------------------------------------------- /src/viz_quadrotor/viz_multiplier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_quadrotor/viz_multiplier.py -------------------------------------------------------------------------------- /src/viz_quadrotor/viz_region.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_quadrotor/viz_region.py -------------------------------------------------------------------------------- /src/viz_quadrotor/viz_trj.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_quadrotor/viz_trj.py -------------------------------------------------------------------------------- /src/viz_tracking/mpc_test_and_viz.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_tracking/mpc_test_and_viz.ipynb -------------------------------------------------------------------------------- /src/viz_tracking/opt_controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_tracking/opt_controller.py -------------------------------------------------------------------------------- /src/viz_tracking/test_and_viz.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization/HEAD/src/viz_tracking/test_and_viz.ipynb --------------------------------------------------------------------------------