@misc{knox2022models,
  title={Models of human preference for learning reward functions},
  author={W. Bradley Knox and Stephane Hatgis-Kessell and Serena Booth and Scott Niekum and Peter Stone and Alessandro Allievi},
  year={2022},
  eprint={2206.02231},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2206.02231}
}