├── .gitignore ├── LICENSE ├── LICENSE-decision-transformer.md ├── README.md ├── architecture-comparison.png ├── clients ├── .gitignore ├── Install.md ├── Readme.md ├── quanser_robots │ ├── Readme.md │ ├── __init__.py │ ├── cartpole │ │ ├── Readme.md │ │ ├── __init__.py │ │ ├── base.py │ │ ├── cartpole.py │ │ ├── cartpole_rr.py │ │ ├── ctrl.py │ │ ├── documentation │ │ │ ├── cartpole.jpg │ │ │ └── model.pdf │ │ └── examples │ │ │ ├── metronom.py │ │ │ ├── plotting_comparison.py │ │ │ ├── realData_230419.npz │ │ │ ├── simData_2304019.npz │ │ │ └── swingup.py │ ├── common.py │ └── qube │ │ ├── Readme.md │ │ ├── __init__.py │ │ ├── base.py │ │ ├── ctrl.py │ │ ├── examples │ │ ├── metronome.py │ │ ├── param_env.py │ │ ├── swing-up.py │ │ └── swing-up_rr.py │ │ ├── model.pdf │ │ ├── qube.py │ │ └── qube_rr.py ├── setup.py └── unify_api.py ├── conda_env.yml ├── data ├── datasets │ └── download_d4rl_datasets.py └── models │ ├── qube_stabilize │ ├── qube-250_dlstm_stabilize-experiments_id1896153_iter40.pt │ ├── qube-250_dt_stabilize-experiments_id1541331_iter40.pt │ └── qube-250_sb-bc_stabilize-experiments_id0096855_iter38.pt │ └── qube_swup │ ├── qube-250_dlstm_swup-experiments_id0099808_iter40.pt │ ├── qube-250_dt_swup-experiments_id1012122_iter40.pt │ └── qube-250_sb-bc_swup-experiments_id8470929_iter36.pt └── src ├── datasets └── info_data.py ├── decision_transformer ├── envs │ ├── assets │ │ └── reacher_2d.xml │ ├── inv_pend.py │ └── reacher_2d.py ├── evaluation │ └── evaluate_episodes.py ├── models │ ├── decision_generic.py │ ├── decision_lstm.py │ ├── decision_transformer.py │ ├── mlp_bc.py │ ├── model.py │ ├── new_mlp_bc.py │ ├── trajectory_gpt2.py │ └── utils.py └── training │ ├── act_trainer.py │ ├── seq_trainer.py │ └── trainer.py ├── eval └── eval_model.py ├── experiment.py └── utils └── create_env.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.zip 2 | *.json 3 | *.pkl 4 | 5 | __pycache__/ 6 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/LICENSE -------------------------------------------------------------------------------- /LICENSE-decision-transformer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/LICENSE-decision-transformer.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/README.md -------------------------------------------------------------------------------- /architecture-comparison.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/architecture-comparison.png -------------------------------------------------------------------------------- /clients/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/.gitignore -------------------------------------------------------------------------------- /clients/Install.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/Install.md -------------------------------------------------------------------------------- /clients/Readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/Readme.md -------------------------------------------------------------------------------- /clients/quanser_robots/Readme.md: -------------------------------------------------------------------------------- 1 | Every directory corresponds to a robot. 2 | -------------------------------------------------------------------------------- /clients/quanser_robots/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/__init__.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/Readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/Readme.md -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/__init__.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/base.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/cartpole.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/cartpole_rr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/cartpole_rr.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/ctrl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/ctrl.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/documentation/cartpole.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/documentation/cartpole.jpg -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/documentation/model.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/documentation/model.pdf -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/examples/metronom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/examples/metronom.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/examples/plotting_comparison.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/examples/plotting_comparison.py -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/examples/realData_230419.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/examples/realData_230419.npz -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/examples/simData_2304019.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/examples/simData_2304019.npz -------------------------------------------------------------------------------- /clients/quanser_robots/cartpole/examples/swingup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/cartpole/examples/swingup.py -------------------------------------------------------------------------------- /clients/quanser_robots/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/common.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/Readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/Readme.md -------------------------------------------------------------------------------- /clients/quanser_robots/qube/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/__init__.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/base.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/ctrl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/ctrl.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/examples/metronome.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/examples/metronome.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/examples/param_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/examples/param_env.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/examples/swing-up.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/examples/swing-up.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/examples/swing-up_rr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/examples/swing-up_rr.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/model.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/model.pdf -------------------------------------------------------------------------------- /clients/quanser_robots/qube/qube.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/qube.py -------------------------------------------------------------------------------- /clients/quanser_robots/qube/qube_rr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/quanser_robots/qube/qube_rr.py -------------------------------------------------------------------------------- /clients/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/setup.py -------------------------------------------------------------------------------- /clients/unify_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/clients/unify_api.py -------------------------------------------------------------------------------- /conda_env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/conda_env.yml -------------------------------------------------------------------------------- /data/datasets/download_d4rl_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/datasets/download_d4rl_datasets.py -------------------------------------------------------------------------------- /data/models/qube_stabilize/qube-250_dlstm_stabilize-experiments_id1896153_iter40.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/models/qube_stabilize/qube-250_dlstm_stabilize-experiments_id1896153_iter40.pt -------------------------------------------------------------------------------- /data/models/qube_stabilize/qube-250_dt_stabilize-experiments_id1541331_iter40.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/models/qube_stabilize/qube-250_dt_stabilize-experiments_id1541331_iter40.pt -------------------------------------------------------------------------------- /data/models/qube_stabilize/qube-250_sb-bc_stabilize-experiments_id0096855_iter38.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/models/qube_stabilize/qube-250_sb-bc_stabilize-experiments_id0096855_iter38.pt -------------------------------------------------------------------------------- /data/models/qube_swup/qube-250_dlstm_swup-experiments_id0099808_iter40.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/models/qube_swup/qube-250_dlstm_swup-experiments_id0099808_iter40.pt -------------------------------------------------------------------------------- /data/models/qube_swup/qube-250_dt_swup-experiments_id1012122_iter40.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/models/qube_swup/qube-250_dt_swup-experiments_id1012122_iter40.pt -------------------------------------------------------------------------------- /data/models/qube_swup/qube-250_sb-bc_swup-experiments_id8470929_iter36.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/data/models/qube_swup/qube-250_sb-bc_swup-experiments_id8470929_iter36.pt -------------------------------------------------------------------------------- /src/datasets/info_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/datasets/info_data.py -------------------------------------------------------------------------------- /src/decision_transformer/envs/assets/reacher_2d.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/envs/assets/reacher_2d.xml -------------------------------------------------------------------------------- /src/decision_transformer/envs/inv_pend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/envs/inv_pend.py -------------------------------------------------------------------------------- /src/decision_transformer/envs/reacher_2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/envs/reacher_2d.py -------------------------------------------------------------------------------- /src/decision_transformer/evaluation/evaluate_episodes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/evaluation/evaluate_episodes.py -------------------------------------------------------------------------------- /src/decision_transformer/models/decision_generic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/decision_generic.py -------------------------------------------------------------------------------- /src/decision_transformer/models/decision_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/decision_lstm.py -------------------------------------------------------------------------------- /src/decision_transformer/models/decision_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/decision_transformer.py -------------------------------------------------------------------------------- /src/decision_transformer/models/mlp_bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/mlp_bc.py -------------------------------------------------------------------------------- /src/decision_transformer/models/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/model.py -------------------------------------------------------------------------------- /src/decision_transformer/models/new_mlp_bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/new_mlp_bc.py -------------------------------------------------------------------------------- /src/decision_transformer/models/trajectory_gpt2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/trajectory_gpt2.py -------------------------------------------------------------------------------- /src/decision_transformer/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/models/utils.py -------------------------------------------------------------------------------- /src/decision_transformer/training/act_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/training/act_trainer.py -------------------------------------------------------------------------------- /src/decision_transformer/training/seq_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/training/seq_trainer.py -------------------------------------------------------------------------------- /src/decision_transformer/training/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/decision_transformer/training/trainer.py -------------------------------------------------------------------------------- /src/eval/eval_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/eval/eval_model.py -------------------------------------------------------------------------------- /src/experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/experiment.py -------------------------------------------------------------------------------- /src/utils/create_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/max7born/decision-lstm/HEAD/src/utils/create_env.py --------------------------------------------------------------------------------