@article{efficientpreferencebasedreinforcement1,
  title = {Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation},
  author = {Fengshuo Bai and Rui Zhao and Hongming Zhang and Sijia Cui and Ying Wen and Yaodong Yang and Bo Xu and Lei Han},
  year = {2024},
  eprint = {2405.18688},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.18688v1},
}