@inproceedings{optimaloffpolicyevaluationfor,
  title = {Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling},
  author = {Tengyang Xie and Yifei Ma and Yu-Xiang Wang},
  year = {2019},
  booktitle = {NeurIPS 2019 12},
  eprint = {1906.03393},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.03393v4},
}