ECAI 2004 Conference Paper

[PDF] [full paper] [prev] [tofc] [next]

Evolution of Communication in a Genetic Based Multi-Agent System: Use Wise Resources

Gilles Enee, Cathy Escazut

We studied how communication evolves in a Multi-Agent System using genetic based machine learning. This work is an extension of a Minimal Model of Communication which consists in making two agents communicating through a medium of communication and playing a naming game with a limited number of situations to recognize. We complexify that model by increasing both the number of agents within the Multi-Agent System and the number of words that can be used by agents. We studied how confusion may emerge through communication and how agents use their available ``cognitive'' ressources in order to learn to communicate. We pointed out that further study with new measures is needed in order to better understand how communication evolves in a genetic based Multi-Agent System.

Keywords: Evolution of communication, Multi-agent systems, Genetic Based Machine Learning, Classifier Systems

Citation: Gilles Enee, Cathy Escazut: Evolution of Communication in a Genetic Based Multi-Agent System: Use Wise Resources. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.1005-1006.

[prev] [tofc] [next]

ECAI-2004 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the Universitat Politècnica de València on behalf of Asociación Española de Inteligencia Artificial (AEPIA) and Associació Catalana d'Intel-ligència Artificial (ACIA).