@article{similarityasrewardalignmentrobustandvers,
  title = {Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning},
  author = {Sara Rajaram and R. James Cotton and Fabian H. Sinz},
  year = {2025},
  eprint = {2506.12529},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.12529},
}