Beyond equilibrium: A dynamical systems approach to learning in games

Bio

Dr. Piliouras is an associate professor at the Singapore University of Technology and Design (SUTD). He received his Ph.D. in Computer Science from Cornell University in 2010. He has held research positions at the Georgia Institute of Technology (GaTech, ECE Dept.) and California Institute of Technology (Caltech, Dept. of Computing and Mathematical Sciences). He has held visiting professor positions at UC Berkeley and DeepMind. He is the recipient of a Singapore NRF Fellowship (2018), a Simons/UC Berkeley Fellowship (2015), a best paper nomination at AAMAS (2019) and a best paper award at AAAI (2021).

Abstract

Historically, Nash equilibrium has been the predominant solution concept in games. We review a recent stream of results on multi-agent learning in standard classes of games (both competitive, e.g. zero-sum games as well as cooperative, e.g. potential games) that showcase how the behavior of standard learning  dynamics can deviate in unexpected ways from the predictions of equilibrium play. A wide range of behaviors is possible, and in fact common, such as cycles, bifurcations, chaos and even simultaneous local stability of Nash equilibrium and chaos. We will end by discussing open questions and challenges.