Skip to Main content Skip to Navigation
Book sections

Contribution to the Control of a MAS's Global Behaviour: Reinforcement Learning Tools

François Klein 1 Christine Bourjot 1 Vincent Chevrier 1
1 MAIA - Autonomous intelligent machine
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Reactive multi-agent systems present global behaviours uneasily linked to their local dynamics. When it comes to controlling such a system, usual analytical tools are difficult to use so specific techniques have to be engineered. We propose an experimental dynamical approach to enhance the control of the global behaviour of a reactive multi-agent system. We use reinforcement learning tools to link global information of the system to control actions. We propose to use the behaviour of the system as this global information. The behaviour of the whole system is controlled thanks to actions at different levels instead of building the behaviours of the agents, so that the complexity of the approach does not directly depend on the number of agents. The controllability is evaluated in terms of rate of convergence towards a target behaviour. We compare the results obtained on a toy example with the usual approach of parameter setting.
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/inria-00400348
Contributor : François Klein <>
Submitted on : Tuesday, June 30, 2009 - 3:34:02 PM
Last modification on : Thursday, January 11, 2018 - 6:19:50 AM
Document(s) archivé(s) le : Monday, October 15, 2012 - 2:55:15 PM

File

klein.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

François Klein, Christine Bourjot, Vincent Chevrier. Contribution to the Control of a MAS's Global Behaviour: Reinforcement Learning Tools. Alexander Artikis and Gauthier Picard and Laurent Vercouter. Engineering Societies in the Agents World IX - 9th International Workshop, ESAW 2008, Saint-Etienne, France, September 24-26, 2008, Revised Selected Papers, 5485, Springer-Verlag Berlin Heidelberg, pp.173-190, 2009, Lecture Notes in Computer Science, 978-3-642-02561-7. ⟨10.1007/978-3-642-02562-4_10⟩. ⟨inria-00400348⟩

Share

Metrics

Record views

482

Files downloads

319