@article{masteringthegameofnopressdiplomacyvia,
  title = {Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning},
  author = {Anton Bakhtin and David J Wu and Adam Lerer and Jonathan Gray and Athul Paul Jacob and Gabriele Farina and Alexander H Miller and Noam Brown},
  year = {2022},
  eprint = {2210.05492},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.05492v1},
}