@article{scposafereinforcementlearningwithsafety, title = {SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization}, author = {Jaafar Mhamed and Shangding Gu}, year = {2023}, eprint = {2311.00880}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.00880v1}, }