@inproceedings{learningpolicieswithzeroorbounded,
  title = {Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs},
  author = {Tao Liu and Ruida Zhou and Dileep Kalathil and P. R. Kumar and Chao Tian},
  year = {2021},
  booktitle = {NeurIPS 2021 12},
  eprint = {2106.02684},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.02684v3},
}