BibTeX record journals/corr/abs-2402-14228

• > Home > journals/corr/abs-2402-14228

@article{DBLP:journals/corr/abs-2402-14228,
  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},
  title        = {{COPR:} Continual Human Preference Learning via Optimal Policy Regularization},
  journal      = {CoRR},
  volume       = {abs/2402.14228},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.14228},
  doi          = {10.48550/ARXIV.2402.14228},
  eprinttype    = {arXiv},
  eprint       = {2402.14228},
  timestamp    = {Wed, 17 Jul 2024 16:21:23 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-14228.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}