@article{modelfreeregretoptimalbestpolicy,
  title = {Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs},
  author = {Zihan Zhou and Honghao Wei and Lei Ying},
  year = {2023},
  eprint = {2309.15395},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.15395v5},
}