Skip to content
forked from tinkoff-ai/CORL

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

License

Notifications You must be signed in to change notification settings

lucas-yyy000/CORL

 
 

Repository files navigation

CORL (Clean Offline Reinforcement Learning)

Getting started

git clone https://github.com/tinkoff-ai/CORL.git && cd CORL
pip install -r requirements/requirements_dev.txt

(downgrade cython if necessary with pip install "cython<3")

Citing CORL

If you use CORL in your work, please use the following bibtex

@inproceedings{
tarasov2022corl,
  title={{CORL}: Research-oriented Deep Offline Reinforcement Learning Library},
  author={Denis Tarasov and Alexander Nikulin and Dmitry Akimov and Vladislav Kurenkov and Sergey Kolesnikov},
  booktitle={3rd Offline RL Workshop: Offline RL as a ''Launchpad''},
  year={2022},
  url={https://openreview.net/forum?id=SyAS49bBcv}
}

About

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 85.3%
  • Python 14.7%