Distributed Learning of Wardrop Equilibria

Abstract : We consider the problem of learning equilibria in a well known game theoretic traffic model due to Wardrop. We consider a distributed learning algorithm that we prove to converge to equilibria. The proof of convergence is based on a differential equation governing the global macroscopic evolution of the system, inferred from the local microscopic evolutions of agents. We prove that the differential equation converges with the help of Lyapunov techniques.
Type de document :
Communication dans un congrès
7th International Conference on Unconventional Computation - UC 2008), Aug 2008, Vienne, Austria. 5204, pp.19--32, 2008, Lecture Notes in Computer Science
Liste complète des métadonnées

https://hal.inria.fr/inria-00308002
Contributeur : Johanne Cohen Épouse Bournez <>
Soumis le : mardi 29 juillet 2008 - 16:17:06
Dernière modification le : jeudi 11 janvier 2018 - 06:21:30

Identifiants

  • HAL Id : inria-00308002, version 1

Collections

Citation

Dominique Barth, Olivier Bournez, Octave Boussaton, Johanne Cohen. Distributed Learning of Wardrop Equilibria. 7th International Conference on Unconventional Computation - UC 2008), Aug 2008, Vienne, Austria. 5204, pp.19--32, 2008, Lecture Notes in Computer Science. 〈inria-00308002〉

Partager

Métriques

Consultations de la notice

262