@article{cao2025residualrewardmodelspreferencebased,
      title={Residual Reward Models for Preference-based Reinforcement Learning}, 
      author={Chenyang Cao and Miguel Rogel-García and Mohamed Nabail and Xueqian Wang and Nicholas Rhinehart},
      year={2025},
      eprint={2507.00611},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2507.00611}, 
}