@article{proximalreinforcementlearningefficientof,
  title = {Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes},
  author = {Andrew Bennett and Nathan Kallus},
  year = {2021},
  eprint = {2110.15332},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.15332v2},
}