Stochastic Approximation, Cooperative Dynamics and Supermodular Games

Michel Benaïm (1) , Mathieu Faure (1)

1 UNINE - Institut de Mathématiques

This paper considers a stochastic approximation algorithm, with decreasing step size and martingale difference noise. Under very mild assumptions, we prove the non convergence of this process toward a certain class of repulsive sets for the associated ordinary differential equation (ODE). We then use this result to derive the convergence of the process when the ODE is cooperative in the sense of [Hirsch, 1985]. In particular, this allows us to extend significantly the main result of [Hofbauer and Sandholm, 2002] on the convergence of stochastic fictitious play in supermodular games.

Mots clés: Game theory; Stochastic approximations; Cooperative dynamical systems; Game theory.

Domaines: Probabilités [math.PR]; Systèmes dynamiques [math.DS]

Michel Benaïm, Mathieu Faure. Stochastic Approximation, Cooperative Dynamics and Supermodular Games. 2010. ⟨hal-00449794⟩