├── .gitignore ├── E&E-RRS ├── .DS_Store ├── README.md ├── TD3.py ├── TD3_MultiQ.py ├── TD3_train.py ├── TD3_train_multiQ.py └── utils.py ├── Exploration-RND ├── README.md ├── RND.py ├── dqn_rnd.py ├── log_utils.py ├── main.py └── smooth_signal.py ├── Offline-BCQ ├── .DS_Store ├── LICENSE(BCQ) └── continuous_BCQ │ ├── .DS_Store │ ├── BCQ.py │ ├── BCQ_Dual.py │ ├── DDPG.py │ ├── README.md │ ├── main.py │ ├── main_MultiQ.py │ └── utils.py ├── Offline-CQL ├── .DS_Store ├── LICENSE ├── README.md ├── examples │ ├── .DS_Store │ ├── cql_antmaze_new.py │ ├── cql_mujoco_new.py │ ├── ddpg.py │ ├── doodad │ │ ├── ec2_example.py │ │ └── gcp_example.py │ ├── dqn_and_double_dqn.py │ ├── her │ │ ├── her_dqn_gridworld.py │ │ ├── her_sac_gym_fetch_reach.py │ │ └── her_td3_multiworld_sawyer_reach.py │ ├── sac.py │ ├── skewfit │ │ ├── sawyer_door.py │ │ ├── sawyer_pickup.py │ │ └── sawyer_push.py │ └── td3.py ├── scripts │ ├── .DS_Store │ ├── run_experiment_from_doodad.py │ ├── run_goal_conditioned_policy.py │ └── run_policy.py └── setup.py ├── README.md └── RebuttalExperiments ├── DDPG.py ├── TD3.py ├── half_cheetah_v3.py ├── main.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/.gitignore -------------------------------------------------------------------------------- /E&E-RRS/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/.DS_Store -------------------------------------------------------------------------------- /E&E-RRS/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/README.md -------------------------------------------------------------------------------- /E&E-RRS/TD3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/TD3.py -------------------------------------------------------------------------------- /E&E-RRS/TD3_MultiQ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/TD3_MultiQ.py -------------------------------------------------------------------------------- /E&E-RRS/TD3_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/TD3_train.py -------------------------------------------------------------------------------- /E&E-RRS/TD3_train_multiQ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/TD3_train_multiQ.py -------------------------------------------------------------------------------- /E&E-RRS/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/E&E-RRS/utils.py -------------------------------------------------------------------------------- /Exploration-RND/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Exploration-RND/README.md -------------------------------------------------------------------------------- /Exploration-RND/RND.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Exploration-RND/RND.py -------------------------------------------------------------------------------- /Exploration-RND/dqn_rnd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Exploration-RND/dqn_rnd.py -------------------------------------------------------------------------------- /Exploration-RND/log_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Exploration-RND/log_utils.py -------------------------------------------------------------------------------- /Exploration-RND/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Exploration-RND/main.py -------------------------------------------------------------------------------- /Exploration-RND/smooth_signal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Exploration-RND/smooth_signal.py -------------------------------------------------------------------------------- /Offline-BCQ/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/.DS_Store -------------------------------------------------------------------------------- /Offline-BCQ/LICENSE(BCQ): -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/LICENSE(BCQ) -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/.DS_Store -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/BCQ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/BCQ.py -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/BCQ_Dual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/BCQ_Dual.py -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/DDPG.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/DDPG.py -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/README.md -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/main.py -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/main_MultiQ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/main_MultiQ.py -------------------------------------------------------------------------------- /Offline-BCQ/continuous_BCQ/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-BCQ/continuous_BCQ/utils.py -------------------------------------------------------------------------------- /Offline-CQL/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/.DS_Store -------------------------------------------------------------------------------- /Offline-CQL/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/LICENSE -------------------------------------------------------------------------------- /Offline-CQL/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/README.md -------------------------------------------------------------------------------- /Offline-CQL/examples/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/.DS_Store -------------------------------------------------------------------------------- /Offline-CQL/examples/cql_antmaze_new.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/cql_antmaze_new.py -------------------------------------------------------------------------------- /Offline-CQL/examples/cql_mujoco_new.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/cql_mujoco_new.py -------------------------------------------------------------------------------- /Offline-CQL/examples/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/ddpg.py -------------------------------------------------------------------------------- /Offline-CQL/examples/doodad/ec2_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/doodad/ec2_example.py -------------------------------------------------------------------------------- /Offline-CQL/examples/doodad/gcp_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/doodad/gcp_example.py -------------------------------------------------------------------------------- /Offline-CQL/examples/dqn_and_double_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/dqn_and_double_dqn.py -------------------------------------------------------------------------------- /Offline-CQL/examples/her/her_dqn_gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/her/her_dqn_gridworld.py -------------------------------------------------------------------------------- /Offline-CQL/examples/her/her_sac_gym_fetch_reach.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/her/her_sac_gym_fetch_reach.py -------------------------------------------------------------------------------- /Offline-CQL/examples/her/her_td3_multiworld_sawyer_reach.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/her/her_td3_multiworld_sawyer_reach.py -------------------------------------------------------------------------------- /Offline-CQL/examples/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/sac.py -------------------------------------------------------------------------------- /Offline-CQL/examples/skewfit/sawyer_door.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/skewfit/sawyer_door.py -------------------------------------------------------------------------------- /Offline-CQL/examples/skewfit/sawyer_pickup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/skewfit/sawyer_pickup.py -------------------------------------------------------------------------------- /Offline-CQL/examples/skewfit/sawyer_push.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/skewfit/sawyer_push.py -------------------------------------------------------------------------------- /Offline-CQL/examples/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/examples/td3.py -------------------------------------------------------------------------------- /Offline-CQL/scripts/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/scripts/.DS_Store -------------------------------------------------------------------------------- /Offline-CQL/scripts/run_experiment_from_doodad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/scripts/run_experiment_from_doodad.py -------------------------------------------------------------------------------- /Offline-CQL/scripts/run_goal_conditioned_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/scripts/run_goal_conditioned_policy.py -------------------------------------------------------------------------------- /Offline-CQL/scripts/run_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/scripts/run_policy.py -------------------------------------------------------------------------------- /Offline-CQL/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/Offline-CQL/setup.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/README.md -------------------------------------------------------------------------------- /RebuttalExperiments/DDPG.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/RebuttalExperiments/DDPG.py -------------------------------------------------------------------------------- /RebuttalExperiments/TD3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/RebuttalExperiments/TD3.py -------------------------------------------------------------------------------- /RebuttalExperiments/half_cheetah_v3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/RebuttalExperiments/half_cheetah_v3.py -------------------------------------------------------------------------------- /RebuttalExperiments/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/RebuttalExperiments/main.py -------------------------------------------------------------------------------- /RebuttalExperiments/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/holarissun/RewardShifting/HEAD/RebuttalExperiments/utils.py --------------------------------------------------------------------------------