@inproceedings{upperconfidenceprimaldualoptimization,
  title = {Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss},
  author = {Shuang Qiu and Xiaohan Wei and Zhuoran Yang and Jieping Ye and Zhaoran Wang},
  year = {2020},
  booktitle = {NeurIPS 2020 12},
  eprint = {2003.00660},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.00660v3},
}