@article{statisticallyefficientvariancereduction,
  title = {Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning},
  author = {Hanhan Zhou and Tian Lan and Vaneet Aggarwal},
  year = {2023},
  eprint = {2308.14897},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.14897v1},
}