Skip to content. Skip to navigation
CIM Menus
 

CIM's 20th Anniversary Seminar Series

Learning Nash Equilibria in Uncoupled Games


Prof. Gabor Lugosi < gabor.lugosi@cs.mcgill.ca >
Department of Economics Pompeu Fabra University
Barcelona Spain

November 18, 2005 at  10:30 AM
Zames Seminar Room - MC437

We construct an uncoupled randomized strategy of repeated play such that, if every player plays according to it, mixed action profiles converge almost surely to a Nash equilibrium of the stage game. The strategy requires very little in terms of information about the game, as players' actions are based only on their own past payoffs.


Moreover, in a variant of the procedure, players need not even know how many other players are there the game. The procedure works for finite generic games and is based on appropriate modifications of a simple stochastic learning rule introduced by Foster and Young.