@article{tighterproblemdependentregretboundsin,
  title = {Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds},
  author = {Andrea Zanette and Emma Brunskill},
  year = {2019},
  eprint = {1901.00210},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1901.00210v4},
}