@inproceedings{bellmanconsistentpessimismforoffline,
  title = {Bellman-consistent Pessimism for Offline Reinforcement Learning},
  author = {Tengyang Xie and Ching-An Cheng and Nan Jiang and Paul Mineiro and Alekh Agarwal},
  year = {2021},
  booktitle = {NeurIPS 2021 12},
  eprint = {2106.06926},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.06926v6},
}