@article{banditlearningthroughbiasedmaximum,
  title = {Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits},
  author = {Xi Liu and Ping-Chun Hsieh and Anirban Bhattacharya and P. R. Kumar},
  year = {2019},
  eprint = {1907.01287},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1907.01287v3},
}