Yongzhao Wang

I am a research associate at The Alan Turing Institute in the UK, where I am working with Prof. Rahul Savani and Prof. Theodore Turocy on the project "Automated Analysis of Strategic Interactions". I received my Ph.D. from the Department of Computer Science at the University of Michigan, advised by Prof. Michael P. Wellman.

My long-term research interests lie in Artificial Intelligence in computer science, with a particular focus on game theory, reinforcement learning, and large language models in the study of multiagent systems. I am also interested in and have actively engaged with relevant applications in financial markets and cybersecurity.

Email: wangyzh@umich.edu

Publications:

[Dec.19] "From Natural Language to Extensive-Form Game Representations". Shilong Deng, Yongzhao Wang, Rahul Savani. In Proceedings of Twenty-Fourth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2025. [paper]
[Oct. 22] "A Strategic Analysis of Prepayments in Financial Credit Networks" (Journal Version). Hao Zhou*, Yongzhao Wang*, Konstantinos Varsos, Nicholas Bishop, Rahul Savani, Anisoara Calinescu, and Michael Wooldridge. *Equal Contribution. Journal of Artificial Intelligence Research, 2024. To Appear.
[Sep. 27] "Market Making with Learned Beta Policies". Yongzhao Wang, Rahul Savani, Anri Gu, Chris Mascioli, Theodore L. Turocy, Michael P. Wellman. In Proceedings of Fifth ACM International Conference on AI in Finance (ICAIF), 2024. [paper]
[Sep. 27] "The Effect of Liquidity on the Spoofability of Financial Markets". Anri Gu, Yongzhao Wang, Chris Mascioli, Mithun Chakraborty, Rahul Savani, Theodore L. Turocy, Michael P. Wellman. In Proceedings of Fifth ACM International Conference on AI in Finance (ICAIF), 2024. [The Winner of the Best Paper Reward] [paper]
[Sep. 27] "A Financial Market Simulation Environment for Trading Agents Using Deep Reinforcement Learning". Chris Mascioli, Anri Gu, Yongzhao Wang, Mithun Chakraborty, Michael P. Wellman. In Proceedings of Fifth ACM International Conference on AI in Finance (ICAIF), 2024. [paper]
[April 24] "A Strategic Analysis of Prepayments in Financial Credit Networks". Hao Zhou*, Yongzhao Wang*, Konstantinos Varsos, Nicholas Bishop, Rahul Savani, Anisoara Calinescu, and Michael Wooldridge. *Equal Contribution. In Proceedings of Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2024. [paper]
[April 24] "Policy Space Response Oracle: A Survey". Ariyan Bighashdel*, Yongzhao Wang*, Stephen McAleer, Rahul Savani, Frans A. Oliehoek. *Equal Contribution. In Proceedings of Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2024. [paper]
[Jan. 24] "Generalized Response Objectives for Strategy Exploration in Empirical Game-Theoretic Analysis". Yongzhao Wang and Michael P. Wellman. In Proceedings of Twenty-Third International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024. [paper]
[Jan. 23] "Empirical Game-Theoretic Analysis for Mean Field Games". Yongzhao Wang and Michael P. Wellman. In Proceedings of Twenty-Second International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023. [paper]
[Jan. 23] "Regularization for Strategy Exploration in Empirical Game-Theoretic Analysis (Extended Abstract)". Yongzhao Wang and Michael P. Wellman. Extended Abstract in Twenty-Second International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023. [paper]
[Jan. 23] "Game Model Learning for Mean Field Games (Extended Abstract)". Yongzhao Wang and Michael P. Wellman. Extended Abstract in Twenty-Second International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023
[Jan. 22] "Evaluating Strategy Exploration in Empirical Game-Theoretic Analysis". Yongzhao Wang, Qiurui Ma and Michael P. Wellman. In Proceedings of Twenty-First International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022. [paper]
[Dec. 21] "Building Action Set in Deep Reinforcement Learner". Yongzhao Wang, Arunesh Sinha, Sky CH-Wang, and Michael P. Wellman. In Proceedings of Twentieth IEEE International Conference on Machine Learning and Applications (ICMLA-21), pages 484–489, 2021. [paper]
[June 19] "Iterated Deep Reinforcement Learning in Games: History-Aware Training for Improved Stability". Mason Wright, Yongzhao Wang, and Michael P. Wellman. In Proceedings of the 20th ACM Conference on Economics and Computation (EC), pages 617-636, June 2019. [paper]
[Feb. 19] "Deception in Finitely Repeated Security Games". Thanh Nguyen, Yongzhao Wang, Arunesh Sinha and Michael P. Wellman. In Proceedings of Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019. [paper]

Teaching:

Lecturer. COMP 226 Computer-Based Trading in Financial Markets. Spring 2025. University of Liverpool.
Lecturer. COMP 226 Computer-Based Trading in Financial Markets. Spring 2024. University of Liverpool.
Graduate Student Instructor. EECS 592 AI Foundations. Winter 2022. University of Michigan.

Invited Talks:

[Oct. 23] Presented "An Introduction to Empirical Game-Theoretic Analysis" in Game Theory and Machine Learning workshop at the London School of Economics and Political Science.
[Feb. 23] Presented the paper "Empirical Game-Theoretic Analysis for Mean Field Games" in Machine Learning and Mean Field Game Seminar.