Speaker Prof. Shinkyu Park
(Electrical and Computer Engineering, KAUST)
Date｜Time Aug 7 (Thurs) 2025｜11:00-12:00
Place Room 316-1, Building 133
Abstract
This talk presents the design, analysis, and application of learning models in large-population games, where agents repeatedly interact by selecting strategies from a common pool. Unlike traditional game-theoretic approaches that assume static cost functions and full information, we consider dynamic payoff mechanisms and learning based on instantaneous feedback.
In the first part, I introduce passivity-based analysis methods from feedback control theory to design learning dynamics that ensure convergence to the Nash equilibrium—where no agent can improve its outcome by unilaterally changing strategies. I also present a higher-order learning model that enhances convergence guarantees, especially in the presence of time delays in strategy updates.
The second part of the talk focuses on applications of this framework. First, we explore multi-robot task allocation, where decentralized learning is used to coordinate mobile robots in dynamic environments. Second, we examine the design of dynamic payoff mechanisms to mitigate endemic transmission in SIRS epidemic models, where agents’ decisions are influenced by stochastic perturbations. Together, these examples demonstrate how population-game-based learning models can support robust and scalable decision-making in complex systems.
Biography
Shinkyu Park (Member, IEEE) received the B.S. degree from Kyungpook National University, Daegu, Korea, in 2006, the M.S. degree from Seoul National University, Seoul, Korea, in 2008, and the Ph.D. degree from the University of Maryland, College Park, MD, USA, in 2015, all in electrical engineering.,From 2016 to 2019, he was a Postdoctoral Associate with the Massachusetts Institute of Technology, and from 2019 to 2021, he was appointed as an Associate Research Scholar with Princeton University. He is currently the Assistant Professor of Electrical and Computer Engineering at King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia. His research interests include robotics, multiagent decision-making, feedback control theory, and game theory.
