@article{contrastiveprefencelearninglearningfrom,
  title = {Contrastive Preference Learning: Learning from Human Feedback without RL},
  author = {Joey Hejna and Rafael Rafailov and Harshit Sikchi and Chelsea Finn and Scott Niekum and W. Bradley Knox and Dorsa Sadigh},
  year = {2023},
  eprint = {2310.13639},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.13639v3},
}