@article{provablyefficientofflinereinforcement,
  title = {Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward},
  author = {Tengyu Xu and Yue Wang and Shaofeng Zou and Yingbin Liang},
  year = {2022},
  eprint = {2206.06426},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2206.06426v2},
}