Principles and Applications of Learning in Large-Population Games.
Shinkyu Park
Assistant Professor
King Abdullah University of Science and Technology
Abstract: In this talk, we discuss the design, analysis, and application of learning models in large-population games. In population games, given a set of strategies, each agent within a population selects a strategy to engage in repeated strategic interactions with others. Rather than computing and adopting the best strategy selection based on a known cost function, agents need to learn this strategy selection from the instantaneous payoffs they receive at each stage of the repeated interactions. Unlike existing formulations in the game theory literature, we consider an underlying mechanism determining the payoffs, which has its own dynamics.
In the first part of this talk, leveraging passivity-based analysis for feedback control systems, I explain principled approaches to designing learning models for agent strategy selection that guarantee convergence to the Nash equilibrium of an underlying game, where no agent can be better off by changing its strategy unilaterally. I also discuss the design of a higher-order learning model that strengthens convergence, which is critical when the agents' strategy selection is subject to time delays. In the second part, we discuss two applications of the large-population games framework: 1) multi-robot task allocation, where a decentralized decision-making model needs to be designed for a team of mobile robots to select and carry out a given set of tasks in dynamically changing environments, and 2) payoff mechanism design to minimize the endemic transmission rate in SIRS epidemics, where the agent's strategy selection is subject to random perturbations.
Biography: Shinkyu Park is the Assistant Professor of Electrical and Computer Engineering and Principal Investigator of Distributed Systems and Autonomy Group at King Abdullah University of Science and Technology (KAUST). Prior to joining KAUST, he was Associate Research Scholar at Princeton University engaged in cross-departmental robotics projects. He received the Ph.D. degree in electrical engineering from the University of Maryland College Park in 2015. Later he held Postdoctoral Fellow positions at the National Geographic Society (2016) and Massachusetts Institute of Technology (2016-2019). Park's research focuses on the learning, planning, and control in multi-agent/multi-robot systems. He is a recipient of 2022 O. Hugo Schuck Best Paper Award (Theory) from the American Automatic Control Council (AACC).
