@article{regularizingamodelbasedpolicystationary,
  title = {Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning},
  author = {Shentao Yang and Yihao Feng and Shujian Zhang and Mingyuan Zhou},
  year = {2022},
  eprint = {2206.07166},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2206.07166v1},
}