@article{oprideofflinepreferencebasedreinforcemen,
  title = {OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration},
  author = {Yiqin Yang and Hao Hu and Yihuan Mao and Jin Zhang and Chengjie Wu and Yuhua Jiang and Xu Yang and Runpeng Xie and Yi Fan and Bo Liu and Yang Gao and Bo Xu and Chongjie Zhang},
  year = {2026},
  eprint = {2604.02349},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.02349},
}