@article{coprcontinualhumanpreferencelearningvia,
  title = {COPR: Continual Human Preference Learning via Optimal Policy Regularization},
  author = {Han Zhang and Lin Gui and Yu Lei and Yuanzhao Zhai and Yehong Zhang and Yulan He and Hui Wang and Yue Yu and Kam-Fai Wong and Bin Liang and Ruifeng Xu},
  year = {2024},
  eprint = {2402.14228},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.14228v3},
}