Canada CIFAR AI Chair and professor of computer science at the University of British Columbia Kevin Leyton-Brown introduces a novel architecture that allows a single network to generalize across different input and output dimensions by using matrix units rather than scalar units, and show that its performance significantly outperforms that of the previous state of the art.
Talk title
“Modeling human play in games: From behavioral economics to deep learning”
Abstract
It is common to assume that players in a game will adopt Nash equilibrium strategies. However, experimental studies have demonstrated that Nash equilibrium is often a poor description of human players' behaviour, even in unrepeated normal-form games. Nevertheless, human behaviour in such settings is far from random. Drawing on data from real human play, the field of behavioral game theory has developed a variety of models that aim to capture these patterns.
The current state of the art in that literature is a model called quantal cognitive hierarchy. It predicts that agents approximately best respond and explicitly model others' beliefs to a finite depth, grounded in a uniform model of non-strategic play. We have shown that even stronger models can be built by drawing on ideas from cognitive psychology to better describe nonstrategic behaviour. However, this whole approach requires extensive expert knowledge and careful choice of functional form. Deep learning presents an alternative, offering the promise of automatic cognitive modeling.
Recommended readings
J. Wright, K. Leyton-Brown. “Predicting Human Behavior in Unrepeated, Simultaneous-Move Games” (PDF). Games and Economic Behavior, Vol. 106, pp. 16–37, November 2017.
J. Wright, K. Leyton-Brown. “Level-0 Models for Predicting Human Behavior in Games.” Journal of Artificial Intelligence Research, Vol. 64, pp. 357–383, February 2019.
J. Wright, K. Leyton-Brown. “Deep Learning for Predicting Human Strategic Behavior” (PDF). Oral presentation at Conference on Neural Information Processing Systems (NIPS), 2016. Spotlight Video on YouTube.
J. Wright, K. Leyton-Brown. “A Formal Separation Between Strategic and Nonstrategic Behavior” (PDF). ACM Conference on Economics and Computation (ACM-EC), 2020.
About Kevin Leyton-Brown
Kevin Leyton-Brown is a member of the Computer Science Department at the University of British Columbia, an associate member of the Vancouver School of Economics, and an associate faculty member at the Alberta Machine Intelligence Institute (Amii).
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by 45 minutes of discussion. Registered attendees will be emailed a Zoom link approximately one hour before the event begins. The event will be recorded and posted online.
Kevin Leyton-Brown