├── README.md ├── agents ├── conservative_sac.py ├── dagger_based_learner.py ├── iql.py └── rlpd.py ├── configs ├── rlpd_config.py └── sac_config.py ├── environment.yml ├── examples ├── train_dagger_main.py ├── train_rlif_main.py └── train_rlif_random_main.py ├── models ├── distributions.py └── model.py ├── plots ├── a.png ├── a1.png ├── a2.png ├── b.png └── c.png ├── scripts ├── run_hopper_random_rlif.sh ├── run_pen_dagger.sh ├── run_pen_hgdagger.sh ├── run_pen_value_based_rlif.sh └── run_walker2d_value_based_rlif.sh └── utils ├── dataset_utils.py ├── env_utils.py ├── jax_utils.py └── utils.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/README.md -------------------------------------------------------------------------------- /agents/conservative_sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/agents/conservative_sac.py -------------------------------------------------------------------------------- /agents/dagger_based_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/agents/dagger_based_learner.py -------------------------------------------------------------------------------- /agents/iql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/agents/iql.py -------------------------------------------------------------------------------- /agents/rlpd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/agents/rlpd.py -------------------------------------------------------------------------------- /configs/rlpd_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/configs/rlpd_config.py -------------------------------------------------------------------------------- /configs/sac_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/configs/sac_config.py -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/environment.yml -------------------------------------------------------------------------------- /examples/train_dagger_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/examples/train_dagger_main.py -------------------------------------------------------------------------------- /examples/train_rlif_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/examples/train_rlif_main.py -------------------------------------------------------------------------------- /examples/train_rlif_random_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/examples/train_rlif_random_main.py -------------------------------------------------------------------------------- /models/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/models/distributions.py -------------------------------------------------------------------------------- /models/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/models/model.py -------------------------------------------------------------------------------- /plots/a.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/plots/a.png -------------------------------------------------------------------------------- /plots/a1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/plots/a1.png -------------------------------------------------------------------------------- /plots/a2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/plots/a2.png -------------------------------------------------------------------------------- /plots/b.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/plots/b.png -------------------------------------------------------------------------------- /plots/c.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/plots/c.png -------------------------------------------------------------------------------- /scripts/run_hopper_random_rlif.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/scripts/run_hopper_random_rlif.sh -------------------------------------------------------------------------------- /scripts/run_pen_dagger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/scripts/run_pen_dagger.sh -------------------------------------------------------------------------------- /scripts/run_pen_hgdagger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/scripts/run_pen_hgdagger.sh -------------------------------------------------------------------------------- /scripts/run_pen_value_based_rlif.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/scripts/run_pen_value_based_rlif.sh -------------------------------------------------------------------------------- /scripts/run_walker2d_value_based_rlif.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/scripts/run_walker2d_value_based_rlif.sh -------------------------------------------------------------------------------- /utils/dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/utils/dataset_utils.py -------------------------------------------------------------------------------- /utils/env_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/utils/env_utils.py -------------------------------------------------------------------------------- /utils/jax_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/utils/jax_utils.py -------------------------------------------------------------------------------- /utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pd-perry/RLIF/HEAD/utils/utils.py --------------------------------------------------------------------------------