Seminar: Utilizing Deep Learning and Game Theory to Find Optimal Policies for a Large Number of Agents

SEMINAR 

DEPARTMENT OF INDUSTRIAL ENGINEERING 

Utilizing Deep Learning and Game Theory to Find Optimal Policies for a Large Number of Agents

Gökçe Dayanıklı

University of Illinois, Urbana-Champaign

Abstract:

In this talk, we will discuss how we can utilize deep learning to solve complex (dynamic and stochastic) game theoretical problems where there are many agents (such as banks, companies, or people) interacting. We will first look at a stochastic optimal control problem for one agent and explain how we can use deep learning to solve this problem. Later, we will move on to the multi-agent setup, and we will discuss and compare two equilibrium notions in game theory: Nash equilibrium and Stackelberg equilibrium. After explaining how a Nash equilibrium can be approximated for dynamic and stochastic games with a large number of agents through mean field games, we will introduce the Stackelberg mean field games between a principal (i.e., regulator) and many agents. Stackelberg mean field game models can be used to find optimal incentives or policies for a large group of noncooperative agents with a motivation to model different real-life problems such as regulating the systemic risk in the banking sector or mitigating the spread of an epidemic. We will discuss how (intrinsically bi-level) Stackelberg mean field game model can be rewritten to propose a single-level deep learning method to solve this complex problem and conclude with some examples.

Keywords: Deep Learning, Game Theory, Optimization

Short Bio: 

Gökçe Dayanıklı is an Assistant Professor of Statistics at the University of Illinois, Urbana-Champaign where she is also an Affiliate Assistant Professor at the Department of Industrial & Enterprise Systems Engineering and an Affiliate at Carl R. Woese Institute for Genomic Biology. Before joining UIUC, she worked as a term assistant professor at Columbia University, Department of Statistics. She completed her Ph.D. in Operations Research & Financial Engineering at Princeton University where she was the recipient of School of Engineering and Applied Science Award for Excellence. During Fall 2021, she was a visiting graduate researcher at the Institute for Mathematical and Statistical Innovation (IMSI) to participate in the "Distributed Solutions to Complex Societal Problems" program. She earned her Bachelor of Science in Industrial Engineering in Boğaziçi University with a minor in Economics. Broadly, she is interested in Mean Field Games & Control, Stackelberg games, and Graphon Games applications, extensions, theory, and solutions.

All interested are cordially invited.  

DATE:  December 23, 2024 

TIME:  Monday, 14:00 

ROOM: Engineering Building, VYKM 2