@article{batchpolicylearninginaveragereward,
  title = {Batch Policy Learning in Average Reward Markov Decision Processes},
  author = {Peng Liao and Zhengling Qi and Runzhe Wan and Predrag Klasnja and Susan Murphy},
  year = {2020},
  eprint = {2007.11771},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2007.11771v3},
}