COPR: Continual Learning Human Preference through Optimal Policy Regularization

@misc{zhang2023copr,
  title = {COPR: Continual Learning Human Preference through Optimal Policy Regularization},
  author = {Han Zhang and Lin Gui and Yuan-Zhao Zhai and Hui Wang and Yu Lei and Ruifeng Xu},
  year = {2023},
  eprint = {2310.15694},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.15694},
}