@inproceedings{statisticallyefficientoffpolicypolicy,
  title = {Statistically Efficient Off-Policy Policy Gradients},
  author = {Nathan Kallus and Masatoshi Uehara},
  year = {2020},
  booktitle = {ICML 2020 1},
  eprint = {2002.04014},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2002.04014v2},
}