@inproceedings{qlearningwithucbexplorationissample,
  title = {Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP},
  author = {Kefan Dong and Yuanhao Wang and Xiaoyu Chen and Li-Wei Wang},
  year = {2019},
  booktitle = {ICLR 2020 1},
  eprint = {1901.09311},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1901.09311v2},
}