@article{areductionfromreinforcementlearningtono,
  title = {A Reduction from Reinforcement Learning to No-Regret Online Learning},
  author = {Ching-An Cheng and Remi Tachet des Combes and Byron Boots and Geoff Gordon},
  year = {2019},
  eprint = {1911.05873},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1911.05873v2},
}