@article{offlinereinforcementlearningwithclosed,
  title = {Offline Reinforcement Learning with Closed-Form Policy Improvement Operators},
  author = {Jiachen Li and Edwin Zhang and Ming Yin and Qinxun Bai and Yu-Xiang Wang and William Yang Wang},
  year = {2022},
  eprint = {2211.15956},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.15956v3},
}