@article{provablymoreefficientqlearninginthe,
  title = {Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings},
  author = {Xiao-Yue Gong and David Simchi-Levi},
  year = {2020},
  eprint = {2007.00080},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2007.00080v2},
}