@article{humanintheloopprovablyefficient,
  title = {Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation},
  author = {Xiaoyu Chen and Han Zhong and Zhuoran Yang and Zhaoran Wang and LiWei Wang},
  year = {2022},
  eprint = {2205.11140},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2205.11140v2},
}