Theoretical Economics, Volume 1, Number 3 (October 2006)

Theoretical Economics 1 (2006), 341–367


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

Dean P. Foster, H. Peyton Young

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

JEL classification: C72, D83

Full Text:  PRINT  VIEW