@inproceedings{zhang:icml21a,
  title = "Average-Reward Off-Policy Policy Evaluation with Function Approximation",
  author = "Zhang, Shangtong and Wan, Yi and Sutton, Richard S and Whiteson, Shimon",
  year = "2021",
  booktitle = "Proceedings of the 38th International Conference on Machine Learning",
  editor = "Meila, Marina and Zhang, Tong",
  month = "18--24 Jul",
  pages = "12578--12588",
  publisher = "PMLR",
  series = "Proceedings of Machine Learning Research",
  url = "http://proceedings.mlr.press/v139/zhang21u.html",
  volume = "139",
}