@article{querypolicymisalignmentinpreferencebased,
  title = {Query-Policy Misalignment in Preference-Based Reinforcement Learning},
  author = {Xiao Hu and Jianxiong Li and Xianyuan Zhan and Qing-Shan Jia and Ya-Qin Zhang},
  year = {2023},
  eprint = {2305.17400},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.17400v3},
}