Learning in a fixed or evolving network of agents

Gauvain Bourgne Amal El Fallah Seghrouchni 1 Henry Soldano
1 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper investigates incremental multiagent learning in static or evolving structured networks. Learning examples are incrementally distributed among the agents, and the objective is to build a common hypothesis that is consistent with all the examples present in the system, despite communication constraints. Recently, a first mechanism was proposed to deal with static networks, but its accuracy was reduced in some topologies. We propose here several possible improvements of this mechanism, whose different behaviors with respect to some efficiency requirements (redundancy, computational cost and communicational cost) are experimentally investigated. Then, we provide an experimental analysis of some variants for evolving networks.
Type de document :
Communication dans un congrès
IEEE Conference on Intelligent Agent technology IAT'2009, 2009, Milan, Italy. IEEE, IEEE Conference on Intelligent Agent technology IAT'2009, pp.549-556, 〈10.1109/WI-IAT.2009.210〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01295287
Contributeur : Lip6 Publications <>
Soumis le : mercredi 30 mars 2016 - 16:49:56
Dernière modification le : jeudi 21 mars 2019 - 13:06:44

Lien texte intégral

Identifiants

Citation

Gauvain Bourgne, Amal El Fallah Seghrouchni, Henry Soldano. Learning in a fixed or evolving network of agents. IEEE Conference on Intelligent Agent technology IAT'2009, 2009, Milan, Italy. IEEE, IEEE Conference on Intelligent Agent technology IAT'2009, pp.549-556, 〈10.1109/WI-IAT.2009.210〉. 〈hal-01295287〉

Partager

Métriques

Consultations de la notice

84