@inproceedings{fan2026boundary,
  title = {Boundary-Seeking Policy Gradient for Safe Reinforcement Learning},
  author = {Chenhua Fan and Jiahui Zhu and Yuhang Zhang and Honghao Wei},
  booktitle = {IEEE Conference on Decision and Control},
  year = {2026},
  url = {https://arxiv.org/pdf/2608.10204}
}

@article{zhu2026tmlr,
  title = {Divide and Conquer: Selective Value Learning and Policy Optimization for Offline Safe Reinforcement Learning},
  author = {Jiahui Zhu and Honghao Wei and Lei Ying},
  journal = {TMLR},
  year = {2026},
  url = {https://openreview.net/pdf?id=4KYrv6qYMl}
}

@inproceedings{zhu2026iclr,
  title = {Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization},
  author = {Jiahui Zhu and Yuanjie Shi and Xiyue Peng and Xin Liu and Yan Yan and Honghao Wei},
  booktitle = {ICLR},
  year = {2026},
  url = {https://openreview.net/forum?id=LrHfYPFTtg}
}

@inproceedings{zhu2025icml,
  title = {Online Constrained Markov Decision Processes},
  author = {Jiahui Zhu and Kihyun Yu and Dabeen Lee and Xin Liu and Honghao Wei},
  booktitle = {ICML},
  year = {2025},
  url = {https://openreview.net/forum?id=fFgiXamW8E}
}