@article{learningoptimaladvantagefrompreferences,
  title = {Learning Optimal Advantage from Preferences and Mistaking it for Reward},
  author = {W. Bradley Knox and Stephane Hatgis-Kessell and Sigurdur Orn Adalgeirsson and Serena Booth and Anca Dragan and Peter Stone and Scott Niekum},
  year = {2023},
  eprint = {2310.02456},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.02456v1},
}