@article{valueincentivizedpreferenceoptimizationa,
  title = {Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF},
  author = {Shicong Cen and Jincheng Mei and Katayoon Goshvadi and Hanjun Dai and Tong Yang and Sherry Yang and Dale Schuurmans and Yuejie Chi and Bo Dai},
  year = {2024},
  eprint = {2405.19320},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.19320v3},
}