@article{strapperpreferencebasedreinforcement,
  title = {STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization},
  author = {Yachen Kang and Li He and Jinxin Liu and Zifeng Zhuang and Donglin Wang},
  year = {2023},
  eprint = {2307.09692},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.09692v1},
}