Matthew Zurek

I am a CS PhD candidate at the University of Wisconsin–Madison. My research focuses on theoretical principles of reinforcement learning. I am also interested more broadly in optimization and statistics. I am very fortunate to be advised by Yudong Chen.

Papers

(* denotes equal contribution)

1. Optimality of a Threshold Policy for a Queueing System with One Fast Server and Two Identical Slow Servers
   Weina Wang, Taha Ameen, Yudong Chen, Yige Hong, Josh Nichols, & Matthew Zurek.
   Preprint, 2026.
   arxiv
2. Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs
   Tianhao Wu, Matthew Zurek, Weina Wang, & Qiaomin Xie.
   Conference on Learning Theory (COLT), 2026.
   arxiv · proceedings
3. Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs
   Guy Zamir, Matthew Zurek, & Yudong Chen.
   Conference on Learning Theory (COLT), 2026.
   arxiv · proceedings
4. Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL
   Matthew Zurek, Guy Zamir, & Yudong Chen.
   Neural Information Processing Systems Conference (NeurIPS), Poster, 2025.
   arxiv · proceedings
5. Faster Fixed-Point Methods for Multichain MDPs. Matthew Zurek & Yudong Chen.
   Neural Information Processing Systems Conference (NeurIPS), Poster, 2025.
   arxiv · proceedings
6. Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL
   Matthew Zurek & Yudong Chen.
   Conference on Learning Theory (COLT), 2025.
   arxiv · proceedings
7. The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
   Matthew Zurek & Yudong Chen.
   International Conference on Algorithmic Learning Theory (ALT), 2025.
   arxiv · proceedings
8. Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
   Matthew Zurek & Yudong Chen.
   Neural Information Processing Systems Conference (NeurIPS), Oral (0.46%), 2024.
   INFORMS Applied Probability Society Best Student Paper Prize Winner
   arxiv · proceedings
9. Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces.
   Brahma S. Pavse, Matthew Zurek, Yudong Chen, Qiaomin Xie, & Josiah P. Hanna.
   International Conference on Machine Learning (ICML), 2024.
   arxiv · proceedings
10. Gap-Free Clustering: Sensitivity and Robustness of SDP
    Matthew Zurek & Yudong Chen.
    Conference on Learning Theory (COLT), 2024.
    arxiv · proceedings
11. The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types
    Gaurav R. Ghosal*, Matthew Zurek*, Daniel S. Brown, Anca Dragan.
    AAAI Conference on Artificial Intelligence, 2023.
    arxiv · proceedings
12. Situational Confidence Assistance for Lifelong Shared Autonomy
    Matthew Zurek*, Andreea Bobu*, Daniel S. Brown, Anca Dragan.
    IEEE International Conference on Robotics and Automation (ICRA), 2021.
    arxiv · proceedings

Awards and Honors

• University of Wisconsin–Madison Cisco Graduate Fellowship (2025)
• INFORMS Applied Probability Society Best Student Paper Prize Winner (2024)
• Institute for Foundations of Data Science Research Assistantship (2023, 2024)
• University of Wisconsin–Madison Computer Sciences Departmental Scholarship (2021)

Teaching

• Guest Lecturer, Nonlinear Optimization I (CS 726), UW–Madison, Spring 2025.
• TA, Nonlinear Optimization I (CS 726), UW–Madison, Spring 2024.
• Head TA, Introduction to Algorithms (CS 577), UW–Madison, Spring 2022.
• TA, Introduction to Algorithms (CS 577), UW–Madison, Fall 2021.

Contact

Email: m@thew.zurek [at] wisc [dot] edu, @=at
Google Scholar
CV