@misc{azar2023general,
  title={A General Theoretical Paradigm to Understand Learning from Human Preferences},
  author={Mohammad Gheshlaghi Azar and Mark Rowland and Bilal Piot and Daniel Guo and Daniele Calandriello and Michal Valko and Rémi Munos},
  year={2023},
  eprint={2310.12036},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2310.12036}
}