@inproceedings{ijcai2022p520,
  title     = {Penalized  Proximal Policy Optimization for Safe Reinforcement Learning},
  author    = {Zhang, Linrui and Shen, Li and Yang, Long and Chen, Shixiang and Wang, Xueqian and Yuan, Bo and Tao, Dacheng},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {3744--3750},
  year      = {2022},
  month     = {7},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2022/520},
  url       = {https://doi.org/10.24963/ijcai.2022/520},
}