@inproceedings{offpolicyevaluationandlearningfrom,
  title = {Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy},
  author = {Yuan Xie and Boyi Liu and Qiang Liu and Zhaoran Wang and Yuan Zhou and Jian Peng},
  year = {2018},
  booktitle = {ICLR 2019 5},
  eprint = {1808.00232},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1808.00232v1},
}