COPR: Continual Human Preference Learning via Optimal Policy Regularization

@inproceedings{zhang2024copr,
  title = {COPR: Continual Human Preference Learning via Optimal Policy Regularization},
  author = {Han Zhang and Lin Gui and Lei Yu 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},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  eprint = {2402.14228},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.14228},
}