Adapting Behaviors Through a Learning Process

Alain Jean-Marie 1 Mabel Tidball 2
1 APR - Algorithmes et Performance des Réseaux
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : This paper concerns the concepts of conjectures and reactions of agents in a dynamic context, a framework where agents form conjectures on how the other agents (would) react to their actions and update this belief according to observations. They decide based on this conjecture without knowing profit functions of other agents. Agents somehow “learn” about the behavior (including the conjectures) of the other agents. We show that some type of “consistency” of these conjectures spontaneously appears. We discuss the Pareto-optimality and the local stability of the strategies obtained in the long run and analyze the example of Cournot’s oligopoly.
Type de document :
Article dans une revue
Journal of Economic Behavior and Organization, Elsevier, 2006, 60 (3), pp.399-422. 〈10.1016/j.jebo.2004.02.007〉
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00102833
Contributeur : Christine Carvalho de Matos <>
Soumis le : lundi 2 octobre 2006 - 16:48:09
Dernière modification le : mardi 13 novembre 2018 - 02:38:01

Identifiants

Citation

Alain Jean-Marie, Mabel Tidball. Adapting Behaviors Through a Learning Process. Journal of Economic Behavior and Organization, Elsevier, 2006, 60 (3), pp.399-422. 〈10.1016/j.jebo.2004.02.007〉. 〈lirmm-00102833〉

Partager

Métriques

Consultations de la notice

145