Abstract
Decision problems can be usually solved using systems that implement different paradigms. These systems may be integrated into a single distributed system, with the expectation of obtaining a group performance more satisfactory than individual performances. Such a distributed system is what we call a Multi Agent Decision System (MADES), a special kind of Multi Agent System, that integrates several heterogeneous autonomous decision systems (agents). A MADES must produce a single solution proposal for the problem instance it faces, despite the fact that its decision making is distributed, and every agent produces solution proposals according to its local view and to its idiosyncrasy. We present a distributed reinforcement algorithm for learning how to combine the decisions the agents make in a distributed way, into a single group decision (solution proposal).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
J. I. Giráldez and D. Borrajo. A distributed model for the combination of heterogeneous knowledge based agents. In J. Hunt, R. Milnes (eds.) “Research and Development in Expert Systems XIV”, December 1997. Proc. of ES97, pp175–184, SGES Publications. 149
Thomas Haynes and Sandip Sen. Evolving behaviorial strategies in predators and prey. In G. Weiss, S. Sen (eds.), Adaption and Learning in Multi Agent Systems Proc. of the IJCAI 95 Workshop, Springer, 1996. 148
Jonathan Schaeffer, Robert Lake, Paul Lu, and Martin Bryant. Chinook, the world man-machine checkers champion. AI Magazine, 17(1):21–29, Spring 1996. 154
G. Weiss. Learning to coordinate actions in multi-agent systems, august 1993. Proc. IJCAI, Chambery, France, volume 1, pp311–316. 148
G. Weiss. Some studies in distributed machine learning and organizational design. Technical Report FKI-189-94, Institut für Informatik, Technische Universität München,1994. 148
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Giráldez, J.I., Borrajo, D. (1998). Distributed Reinforcement Learning in Multi-agent Decision Systems. In: Coelho, H. (eds) Progress in Artificial Intelligence — IBERAMIA 98. IBERAMIA 1998. Lecture Notes in Computer Science(), vol 1484. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49795-1_13
Download citation
DOI: https://doi.org/10.1007/3-540-49795-1_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64992-2
Online ISBN: 978-3-540-49795-0
eBook Packages: Springer Book Archive