@article{offlinereinforcementlearningwith2,
  title = {Offline Reinforcement Learning with Realizability and Single-policy Concentrability},
  author = {Wenhao Zhan and Baihe Huang and Audrey Huang and Nan Jiang and Jason D. Lee},
  year = {2022},
  eprint = {2202.04634},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2202.04634v3},
}