@inproceedings{regretminimizationforreinforcement,
  title = {Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function},
  author = {Zihan Zhang and Xiangyang Ji},
  year = {2019},
  booktitle = {NeurIPS 2019 12},
  eprint = {1906.05110},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.05110v3},
}