@article{offpolicyprimaldualsafereinforcement,
  title = {Off-Policy Primal-Dual Safe Reinforcement Learning},
  author = {Zifan Wu and Bo Tang and Qian Lin and Chao Yu and Shangqin Mao and Qianlong Xie and Xingxing Wang and Dong Wang},
  year = {2024},
  eprint = {2401.14758},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.14758v2},
}