@article{doublereinforcementlearningforefficient,
  title = {Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes},
  author = {Nathan Kallus and Masatoshi Uehara},
  year = {2019},
  eprint = {1908.08526},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.08526v3},
}