Zun Li

Email: lizun [at] umich [dot] edu

I am a fifth-year Ph.D. in Computer Science of Strategic Reasoning Group at University of Michigan. My advisor is Prof. Michael P. Wellman.

In summer 2022, I worked as a research scientist intern in DeepMind Alberta, mentored by Dr. Marc Lanctot.

I completed my bachlor degree at Shanghai Jiao Tong University, majoring in Computer Science. I was a research assistant at Advanced Network Lab, advised by Prof. Fan Wu and Dr. Zhenzhe Zheng.

Education

University of Michigan, U.S., from Sep. 2018 to Now
Ph.D. Student in Computer Science and Engineering

Shanghai Jiao Tong University, China, from Sep. 2014 to Jun. 2018
B.S.E. in Computer Science (IEEE Honored Class)

Research Interests

My research interests lie in computer game AI. I am interested in computational game theory, (deep) multi-agent learning / planning, game-tree search, and agent-based simulation methods.

Publications

Conference Publications

[6] "Search-Improved Game-Theoretic Multiagent Reinforcement Learning in General and Negotiation Games (Extended Abstract)"[arXiv]
Zun Li, Marc Lanctot, Kevin McKee, Luke Marris, Ian Gemp, Daniel Hennes, Paul Muller, Kate Larson, Yoram Bachrach, Michael P. Wellman
To Appear in Twenty-Second International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
458/1015≈45.1% accepted for full paper + extended abstract.
In submission for full-paper publication.

[5] "Solving Structured Hierarchical Games Using Differential Backward Induction"[PDF]
Zun Li, Feiran Jia, Aditya Mate, Shahin Jabbari, Mithun Chakraborty, Milind Tambe, Yevgeniy Vorobeychik
In Proceedings of Thirty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI),2022.
36/712≈5.06% accepted for oral presentation
Also presented at First ICLR Workshop on Gamification and Multiagent Solutions (ICLR-GMAS), 2022.

[4] "Evolution Strategies for Approximate Solution of Bayesian Games"[PDF][TALK][SLIDES][POSTER]
Zun Li, Michael P. Wellman
In Proceedings of Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021.
1692/7911≈21.38% accepted for pre-recorded video talk
Also presented at Third Games, Agents, and Incentives Workshop (GAIW@AAMAS), 2021.

[3] "Structure Learning for Approximate Solution of Many-Player Games" [PDF][SLIDES][POSTER]
Zun Li, Michael P. Wellman
In Proceedings of Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020.
453/7731≈5.85% accepted for oral presentation

[2] "Bounding Regret in Empirical Games" [PDF]
Steven Jecmen, Arunesh Sinha, Zun Li, Long Tran-Thanh
In Proceedings of Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020.
1137/7731≈14.7% accepted for spotlight presentation

[1] "On Designing Optimal Data Purchasing Strategies for Online Ad Auctions" [PDF]
Zun Li, Zhenzhe Zheng, Fan Wu, Guihai Chen
In Proceedings of Seventeenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018.
151/591≈25.55% accepted for oral presentation

Journal Publications

[1] "Capitalize Your Data: Optimal Selling Mechanisms for IoT Data Exchange"[PDF]
Qinya Li, Zun Li, Zhenzhe Zheng, Fan Wu , Shaojie Tang, Zhao Zhang, Guihai Chen
IEEE Transactions on Mobile Computing, 2021

Working Experience

DeepMind Alberta, Research Scientist Intern, Edmonton, Jun. 2022-Nov. 2022
Google Inc., Software Engineering Intern, Core Google Display Ad Team, Remote, Jun. 2021-Aug. 2021

Teaching Experience

Graduate Student Instructor, EECS 592 AI Foundations, UMich, Fall'21

Blogs

How many possible combinations of airplane+solo are there in Dou Dizhu?


This guy designed this neat webpage.