Learning from multiple sources

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2004

Autores

Luís Nunes (Autor) Outra; Eugénio Oliveira (Autor) FEUP

Ata de Conferência Internacional

Título: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004

Páginas: 1106-1113

3rd International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2004), 19-23 August 2004, New York, NY, USA

Indexação

ISI Web of Knowledge

Scopus - 22 Citações

Classificação Científica

CORDIS: Ciências Físicas > Ciência de computadores > Cibernética > Inteligência artificial

Outras Informações

ID Authenticus: P-007-MAY

DOI: 10.1109/aamas.2004.10162

Abstract (EN): This work aims at defining and testing a set of techniques that enables agents to use information from several sources during learning. In Multiagent Systems (MAS) it is frequent that several agents need to learn similar concepts in parallel. In this type of environment there are more possibilities for learning than in classical Machine Learning. Exchange of information between teams of agents that are attempting to solve similar problems may increase accuracy and learning speed at the expense of communication. One of the most interesting possibilities to explore is when the agents may have different structures and learning algorithms, thus providing different perspectives on the problems they are facing. In this paper the authors report the results of experiments made in a traffic control simulation with and without exchanging information between learning agents.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 8