@article{dprdiffusionpreferencebasedrewardfor,
  title = {DPR: Diffusion Preference-based Reward for Offline Reinforcement Learning},
  author = {Teng Pang and Bingzheng Wang and Guoqiang Wu and Yilong Yin},
  year = {2025},
  eprint = {2503.01143},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.01143v2},
}