Preprints

• Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs. [arXiv]
  Zihan Zhou, Honghao Wei, and Lei Ying.
  

Selected Publications

• Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization.
  Jiahui Zhu, Yuanjie Shi, Xiyue Peng, Xin Liu, Yan Yan, Honghao Wei.
  ICLR, 2026.
  

• Towards Fast Safe Online Reinforcement Learning via Policy Finetuning. [PDF]
  Keru Chen, Honghao Wei, Zhigang Deng, Sen Lin.
  TMLR, 2025.
  

• Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems. [PDF]
  Xin Liu, Honghao Wei, and Lei Ying.
  IEEE Trans. TON, 2025.
  

• Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization. [PDF] [Code]
  Xiyue Peng, Hengquan Guo, Jiawei Zhang, Dongqing Zou, Ziyu Shao, Honghao Wei, Xin Liu.
  NeurIPS, 2025.
  

• An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints. [PDF]
  Jiahui Zhu, Kihyun Yu, Dabeen Lee, Xin Liu, Honghao Weia.
  ICML, 2025.
  

• Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning. [PDF]
  Yassine Chemingui, Aryan Deshwal, Honghao Wei, Alan Fern, Janardhan Rao Doppa.
  AAAI, 2025 (oral).
  

• Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning. [PDF]
  Honghao Wei, Xiyue Peng, Arnob Ghosh, Xin Liu.
  NeurIPS, 2024.
  

• Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage. [PDF]
  Haobo Zhang, Xiyue Peng, Honghao Wei, Xin Liu.
  NeurIPS, 2024.
  

• Optimistic Joint Flow Control and Link Scheduling with Unknown Utility Functions. [PDF]
  Xin Liu, Honghao Wei, Lei Ying.
  MobiHoc, 2024.
  

• Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis. [PDF]
  Qining Zhang, Honghao Wei, Lei Ying.
  RLC, 2024.
  

• Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration. [PDF]
  Honghao Wei, Xin Liu, and Lei Ying.
  AAAI, 2024 (oral).
  

• Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks. [PDF]
  Honghao Wei, Xin Liu, Weina Wang, and Lei Ying.
  NeurIPS, 2023 (spotlight, \~3% acceptance).
  

• A Reinforcement Learning and Prediction-Based Lookahead Policy for Vehicle Repositioning in Online Ride-Hailing Systems. [PDF] [Code]
  Honghao Wei, Zixian Yang, Xin Liu, Zhiwei (Tony) Qin, Xiaocheng Tang, and Lei Ying.
  IEEE Trans. ITS, 2023.
  

• Provably Efficient Model-Free Algorithms for Non-stationary CMDPs. [PDF]
  Honghao Wei, Arnob Ghosh, Xingyu Zhou, Lei Ying, and Ness Shroff.
  AISTATS, 2023.
  

• Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond. [PDF]
  Hengquan Guo, Xin Liu, Honghao Wei, and Lei Ying.
  NeurIPS, 2022.
  

• Triple-Q: A Model-Free Algorithm for Constrained Reinforcement Learning with Sublinear Regret and Zero Constraint Violation. [PDF]
  Honghao Wei, Xin Liu, and Lei Ying.
  AISTATS, 2022.
  

• A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes. [PDF]
  Honghao Wei, Xin Liu, and Lei Ying.
  AAAI, 2022.
  

• On Low-Complexity Quickest Intervention of Mutated Diffusion Processes Through Local Approximation. [PDF]
  Qining Zhang, Honghao Wei, Weina Wang, and Lei Ying.
  MobiHoc, 2022.
  

• Fork: A forward-looking actor for model-free reinforcement learning. [PDF] [Code]
  Honghao Wei, and Lei Ying.
  CDC 2021.
  

• QuickStop: A Markov Optimal Stopping Approach for Quickest Misinformation Detection. [PDF]
  Honghao Wei, Xiaohan Kang, Weina Wang, and Lei Ying.
  SIGMEETRICS, 2019.