@article{howtoqueryhumanfeedbackefficientlyinrl,
  title = {Provable Reward-Agnostic Preference-Based Reinforcement Learning},
  author = {Wenhao Zhan and Masatoshi Uehara and Wen Sun and Jason D. Lee},
  year = {2023},
  eprint = {2305.18505},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.18505v3},
}