A simple pytorch reimplementation for Conservative Q-Learning for Offline Reinforcement Learning (https://arxiv.org/abs/2006.04779).
@article{kumar2020conservative,
author = {Aviral Kumar and Aurick Zhou and George Tucker and Sergey Levine},
title = {Conservative Q-Learning for Offline Reinforcement Learning},
conference = {arXiv Pre-print},
url = {https://arxiv.org/abs/2006.04779},
}
@misc{CQL-pytorch,
author = {Wei-Cheng Tseng},
title = {WeiChengTseng/CQL-pytorch},
url = {https://github.com/WeiChengTseng/CQL-pytorch},
year = {2022}
}