Anzeige
Erschienen in:
1996 | ReviewPaper | Buchkapitel
Learning in multi-robot systems
verfasst von : Maja J. Matarić
Erschienen in: Adaption and Learning in Multi-Agent Systems
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper discusses why traditional reinforcement learning methods often result in poor performance in dynamic, situated multiagent domains characterized by multiple goals, noisy perception and action, and inconsistent reinforcement. We propose a methodology for designing the representation and the forcement functions that take advantage of implicit domain knowledge in order to accelerate learning in such domains, and demonstrate it experimentally in two different mobile robot domains.