Picture of James

Contact

Dept. of Computing Science
University of Alberta
Edmonton, Alberta, Canada
T6G 2E8

Office: Athabasca Hall 3-57

james.wright@ualberta.ca

"That's your game theory? Rock Paper Scissors with statistics?"
— Peter Watts, Blindsight

James R. Wright

Hello, I'm James Wright. I am an Assistant Professor at the University of Alberta. I also hold a Canada CIFAR Artificial Intelligence Chair and am a Fellow of the Alberta Machine Intelligence Institute. Previously I was a postdoctoral researcher at Microsoft Research in New York City. I completed my Ph.D. at the University of British Columbia in 2016, advised by Kevin Leyton-Brown.

Research

My primary research interest is in using data-driven machine learning models to predict human strategic behavior; that is, behavior in interactions where each participant's rewards depend partially on the actions of other participants. My long-term research agenda is to build a general theory for optimally designing algorithms for mediating interactions involving humans or other realistically bounded agents rather than idealized, perfectly rational game theoretic agents.

Curriculum Vitae

My academic CV is available as both an HTML page and a PDF document. I also have a public Google Scholar citations page.

Publications

  1. Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization.
    Ryan D'Orazio, Dustin Morrill, James R. Wright, and Michael Bowling.
    AAMAS 2020: 19th International Conference on Autonomous Agents and Multiagent Systems, 2020
  2. Learning When to Stop Searching.
    Daniel G. Goldstein, R. Preston McAfee, Siddarth Suri, and James R. Wright.
    Management Science 66:3, pages 1375--1394, March 2020.
    (Full version of Goldstein et al. [2017])
  3. Bounds for Approximate Regret-Matching Algorithms.
    Ryan D'Orazio, Dustin Morrill, James R. Wright.
    Bridging Game Theory and Deep Learning Workshop at NeurIPS, 2019.
  4. A Formal Separation Between Strategic and Nonstrategic Behavior.
    James R. Wright and Kevin Leyton-Brown.
    Workshop on Behavioral EC at ACM Conference on Economics and Computation, 2019.
  5. Incentivizing Evaluation with Peer Prediction and Limited Access to Ground Truth.
    Xi Alice Gao, James R. Wright, and Kevin Leyton-Brown.
    Artificial Intelligence. 275, 2019.
  6. Level-0 Models for Predicting Human Behavior in Games.
    James R. Wright and Kevin Leyton-Brown.
    Journal of Artificial Intelligence Research, Volume 64, pages 357–383, February 2019.
    (supersedes Wright & Leyton-Brown [2014])
  7. Predicting Human Behavior in Unrepeated, Simultaneous-Move Games.
    James R. Wright and Kevin Leyton-Brown.
    Games and Economic Behavior, Volume 106, pages 16–37, November 2017.
    (supersedes Wright & Leyton-Brown [2010, 2012])
  8. Learning in the Repeated Secretary Problem.
    Daniel G. Goldstein, R. Preston McAfee, Siddarth Suri, and James R. Wright.
    ACM Conference on Economics and Computation (ACM-EC), 2017.
    (Abstract)
  9. Deep Learning for Predicting Human Strategic Behavior.
    Jason Hartford, James R. Wright, and Kevin Leyton-Brown.
    NIPS 2016: Thirtieth Annual Conference on Neural Information Processing Systems, 2016.
    Oral presentation.
  10. Incentivizing Evaluation via Limited Access to Ground Truth: Peer-Prediction Makes Things Worse.
    Xi Alice Gao, James R. Wright, and Kevin Leyton-Brown.
    Workshop on Algorithmic Game Theory and Data Science at ACM Conference on Economics and Computation, 2016.
  11. Mechanical TA: Partially Automated High-Stakes Peer Grading.
    James R. Wright, Chris Thornton, Kevin Leyton-Brown.
    ACM Technical Symposium on Computer Science Education (ACM-SIGCSE), 2015
  12. Level-0 Meta-Models for Predicting Human Behavior in Games.
    James R. Wright and Kevin Leyton-Brown.
    ACM Conference on Economics and Computation (ACM-EC), 2014.
  13. Behavioral Game-Theoretic Models: A Bayesian Framework For Parameter Analysis.
    James R. Wright and Kevin Leyton-Brown.
    Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), pages 921–928, 2012.
    Best student paper (runner up).
  14. Linear solvers for nonlinear games: using pivoting algorithms to find Nash equilibria in n-player games.
    James R. Wright, Albert Xin Jiang, and Kevin Leyton-Brown.
    SIGecom Exchanges, volume 10, number 1, pages 9–12, 2011.
  15. Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
    James R. Wright and Kevin Leyton-Brown.
    Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI-10), pages 901–907, 2010.

Propspective Students

Prospective M.Sc. students who are not currently enrolled at the University of Alberta, please do not contact me directly. Instead, apply to my department and indicate an interest in working with me. I am likely to take on new Ph.D. students from outside U of A only when I am familiar with their publications in my area. I am likely to take on other students for an M.Sc. with the possibility of continuing to a Ph.D.

For students who are already at U of A, please take my grad class if you are interested in working with me.

Last update: Mar 12/2020