@article{nashlearningfromhumanfeedback,
  title = {Nash Learning from Human Feedback},
  author = {Rémi Munos and Michal Valko and Daniele Calandriello and Mohammad Gheshlaghi Azar and Mark Rowland and Zhaohan Daniel Guo and Yunhao Tang and Matthieu Geist and Thomas Mesnard and Andrea Michi and Marco Selvi and Sertan Girgin and Nikola Momchev and Olivier Bachem and Daniel J. Mankowitz and Doina Precup and Bilal Piot},
  year = {2023},
  eprint = {2312.00886},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.00886v4},
}