Regret testing: learning to play Nash equilibrium without knowing you have an opponent

Dean P. Foster () and H. Peyton Young ()

Theoretical Economics, 2006, vol. 1, issue 3, pages 341-367

Abstract: A learning rule is uncoupled if a player does not condition his strategy on the opponent's payoffs. It is radically uncoupled if a player does not condition his strategy on the opponent's actions or payoffs. We demonstrate a family of simple, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any finite two-person game.

Keywords: Learning; Nash equilibrium; regret; bounded rationality (search for similar items in EconPapers)
JEL-codes: C72 D83 (search for similar items in EconPapers)
Date: 2006 Written 2006-09-07
View citations in EconPapers

Downloads: (external link)
http://econtheory.org/ojs/index.php/te/article/view/20060341/31 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Access Statistics for this article

Theoretical Economics is edited by Jeffrey C. Ely, Edward Green, Barton L. Lipman, Martin J. Osborne, and Debraj Ray

More articles in Theoretical Economics from Society for Economic Theory
Series data maintained by Martin J. Osborne ().