@article{personalizingreinforcementlearningfrom,
  title = {Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning},
  author = {Sriyash Poddar and Yanming Wan and Hamish Ivison and Abhishek Gupta and Natasha Jaques},
  year = {2024},
  eprint = {2408.10075},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.10075v1},
}