@article{exploratorypreferenceoptimization,
  title = {Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF},
  author = {Tengyang Xie and Dylan J. Foster and Akshay Krishnamurthy and Corby Rosset and Ahmed Awadallah and Alexander Rakhlin},
  year = {2024},
  eprint = {2405.21046},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.21046v1},
}