Honghao Wei
 |
Assistant Professor |
About me
I am an assistant professor in the School of Electrical Engineering and Computer Science at Washington State University (WSU). I received my Ph.D. degree from the Department of Electrical Engineering and Computer Science at the University of Michigan, Ann Arbor, 2023, advised by Prof. Lei Ying. My research interests lie in designing scalable, efficient, and practical machine learning algorithms with strong theoretical guarantees.
To Prospective Students
I have multiple fully-funded Ph.D. openings in my group at WSU.
I am looking for highly motivated students with strong backgrounds in mathematics, reinforcement learning, machine learning, and optimization to work with me.
Moreover, interns and visiting students are highly welcome!
Please shoot me an email if you are interested in working with me. Please include your resume, and undergraduate / graduate transcripts.
Research
My research interests include
Online Learning and Decision-making
Reinforcement Learning and Constrained Reinforcement Learning
Stochastic Modeling, Analysis and Optimization
Reinforcement Learning with Applications in Communication, Ride-hailing, and Social Networks
News!
09/2024: Two papers on offline Safe-RL, focusing on robust policy improvement and addressing the partial coverage issue, have been accepted to NeurIPS 2024. Congrats to all the collaborators!
08/2024: Our work on Optimistic Joint Flow Control and Link Scheduling with Unknown Utility Functions has been accepted by MobiHoc 2024.
05/2024: Invited to serve as a TPC member for INFOCOM 2025.
05/2024: Our work on Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis has been accepted by Reinforcement Learning Conference (RLC).
12/2023: Our work on safe Reinforcement Learning with instantaneous constraints has been accepted by AAAI 2024 as a oral presentation. We studied the role of aggressive policy exploration in safe RL. Check it out!
10/2023: New manuscript out: Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs. We proposed the first model-free algorithm for best policy identification in tabular CMDPs. Check it out!
09/2023: Our work on using augmented samples to improve sample efficiency in mixed systems has been accepted by NeurIPS 2023 as a spotlight presentation.
09/2023: Our work on using RL with prediction-based lookahead policy for vehicle repositioning in ride-hailing systems has been accepted by IEEE Transactions on Intelligent Transportation Systems.
08/2023: Defended my Ph.D. dissertation.
04/2023: Invited to serve as a TPC member for INFOCOM 2024.
Preprints
Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs. [arXiv]
Zihan Zhou, Honghao Wei, and Lei Ying.
Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems. [arXiv]
Xin Liu, Honghao Wei, and Lei Ying.
Selected Publications
Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration. [PDF]
Honghao Wei, Xin Liu, and Lei Ying.
AAAI oral, 2024.
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 spotlight, 2023 (~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.
Professional Service
Conference Reviewer: ICLR 24 / NeurIPS 22, 23, 24 / ICML 22, 23, 24 / AAAI 22, 23, 24 / AISTATS 22, 23, 24 / INFOCOM 24 / KDD-OnlineMarketplaces 22, 23 / ISIT 21 / CDC 21 / RL4ITS 21 /
Journal Reviewer: IEEE Trans. Inf. Theory / Netw / Control. Netw. Syst.