I was reading this neat piece by Fudenberg http://fudenberg.fas.harvard.edu/predictive%20game%20theory.pdf on Predictive Game Theory. He argues correctly that most traditional work in Game Theory is not suited for prediction in real world set-ups.

Do you know any work that has advanced the theory or empirics of predictive game theory?

I am aware of some recent work of partial identification for games but I am more interested in learning in games and off-equilibrium dynamics.


1 Answer 1


Actually, Section 3 of the paper you linked is probably one of the most comprehensive lists you could find of the movers and the shakers with regard to predictive game theory. I know that many of them have both published and working papers addressing these issues. Fudenberg even addresses those specific two topics. A few selections from the paper:

Ignacio Esponda, Philippe Jehiel, and David K. Levine are leaders in studying adaptive processes in extensive form games, and the sorts of non-Nash equilibrium outcomes that can persist even when players have a lot of experience with the game.

Michel Benaïm, Josef Hofbauer, William Sandholm, and Sylvain Sorin are making important advances in the mathematics of dynamical systems and applying them to non-equilibrium dynamics.

Chaim Fershtman and Ariel Pakes are developing estimation methods for field data that allow for incorrect off-path beliefs.

Jeff Shamma is a pioneer in bringing techniques from the feedback-control literature to the study of learning in games.

I would recommend going through these authors' websites and looking for papers that fit.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.