@article{reinforcementlearningfromdiversehuman,
  title = {Reinforcement Learning from Diverse Human Preferences},
  author = {Wanqi Xue and Bo An and Shuicheng Yan and Zhongwen Xu},
  year = {2023},
  eprint = {2301.11774},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2301.11774v3},
}