@article{safeexplorationforconstrained,
  title = {DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning},
  author = {Archana Bura and Aria HasanzadeZonuzy and Dileep Kalathil and Srinivas Shakkottai and Jean-Francois Chamberland},
  year = {2021},
  eprint = {2112.00885},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.00885v3},
}