35 citations · 57 across the 6 of their papers we have counts for
8 papers
Learning with minimal information in continuous games
Sebastian Bervoets, Mario Bravo, Mathieu Faure
We introduce a stochastic learning process called the dampened gradient approximation process. While learning models have almost exclusively focused on finite games, in this paper…
Convergence of generalized urn models to non-equilibrium attractors
Mathieu Faure, Sebastian Schreiber
Generalized Polya urn models have been used to model the establishment dynamics of a small founding population consisting of k different genotypes or strategies. As population size…
Reinforcement learning with restrictions on the action set
Mario Bravo, Mathieu Faure
Consider a 2-player normal-form game repeated over time. We introduce an adaptive learning procedure, where the players only observe their own realized payoff at each stage. We ass…
Consistency of vanishing smooth fictitious play
Michel Benaïm, Mathieu Faure
We discuss consistency of Vanishing Smooth Fictitious Play, a strategy in the context of game theory, which can be regarded as a smooth fictitious play procedure, where the smoothi…
Quasi-stationary distributions for randomly perturbed dynamical systems
Mathieu Faure, Sebastian J. Schreiber
We analyze quasi-stationary distributions of a family of Markov chains that are random perturbations of…
Ergodic Properties of weak Asymptotic Pseudotrajectories for Set-valued Dynamical Systems
Mathieu Faure, Gregory Roth
A successful method to describe the asymptotic behavior of various deterministic and stochastic processes such as asymptotically autonomous differential equations or stochastic app…
Stochastic Approximation, Cooperative Dynamics and Supermodular Games
Michel Benaïm, Mathieu Faure
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 t…
Stochastic approximations of set-valued dynamical systems: Convergence with positive probability to an attractor
Mathieu Faure, Gregory Roth
A succesful method to describe the asymptotic behavior of a discrete time stochastic process governed by some recursive formula is to relate it to the limit sets of a well chosen m…