├── .gitignore ├── LICENSE ├── README.md ├── iql.py ├── main_iql.py ├── main_por.py ├── models ├── hopper-medium-expert-v2 │ └── pretrain_step-1000000_normalize-False-behavior_goal_network ├── hopper-medium-replay-v2 │ └── pretrain_step-1000000_normalize-False-behavior_goal_network └── hopper-medium-v2 │ └── pretrain_step-1000000_normalize-False-behavior_goal_network ├── policy.py ├── por.py ├── pretrain.sh ├── requirements.txt ├── run_antmaze_iql.sh ├── run_antmaze_por.sh ├── run_mujoco_iql.sh ├── run_mujoco_por.sh ├── util.py └── value_functions.py /.gitignore: -------------------------------------------------------------------------------- 1 | /wandb/ 2 | /results/ 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/README.md -------------------------------------------------------------------------------- /iql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/iql.py -------------------------------------------------------------------------------- /main_iql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/main_iql.py -------------------------------------------------------------------------------- /main_por.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/main_por.py -------------------------------------------------------------------------------- /models/hopper-medium-expert-v2/pretrain_step-1000000_normalize-False-behavior_goal_network: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/models/hopper-medium-expert-v2/pretrain_step-1000000_normalize-False-behavior_goal_network -------------------------------------------------------------------------------- /models/hopper-medium-replay-v2/pretrain_step-1000000_normalize-False-behavior_goal_network: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/models/hopper-medium-replay-v2/pretrain_step-1000000_normalize-False-behavior_goal_network -------------------------------------------------------------------------------- /models/hopper-medium-v2/pretrain_step-1000000_normalize-False-behavior_goal_network: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/models/hopper-medium-v2/pretrain_step-1000000_normalize-False-behavior_goal_network -------------------------------------------------------------------------------- /policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/policy.py -------------------------------------------------------------------------------- /por.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/por.py -------------------------------------------------------------------------------- /pretrain.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/pretrain.sh -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/requirements.txt -------------------------------------------------------------------------------- /run_antmaze_iql.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/run_antmaze_iql.sh -------------------------------------------------------------------------------- /run_antmaze_por.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/run_antmaze_por.sh -------------------------------------------------------------------------------- /run_mujoco_iql.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/run_mujoco_iql.sh -------------------------------------------------------------------------------- /run_mujoco_por.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/run_mujoco_por.sh -------------------------------------------------------------------------------- /util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/util.py -------------------------------------------------------------------------------- /value_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ryanxhr/POR/HEAD/value_functions.py --------------------------------------------------------------------------------