A BEJTE Contributions article.

Abstract

This paper extends the convergence result in Kalai and Lehrer (1993a, 1993b) to a class of games where players have a payoff function continuous for the product topology. Provided that 1) every player maximizes her expected payoff against her own beliefs, 2) every player updates her beliefs in a Bayesian manner, and 3) prior beliefs of other players' strategies have a grain of truth, we construct a Nash equilibrium such that, after some finite time, the equilibrium outcome of the above game is arbitrarily close to the constructed Nash equilibrium.

Submitted: February 22, 2008 · Accepted: October 3, 2008 · Published: January 21, 2009

Recommended Citation

Leoni, Patrick L. (2008) "A Constructive Proof that Learning in Repeated Games Leads to Nash Equilibria," The B.E. Journal of Theoretical Economics: Vol. 8 : Iss. 1 (Contributions), Article 29.
DOI: 10.2202/1935-1704.1462
Available at: http://www.bepress.com/bejte/vol8/iss1/art29