Abstract
We are currently investigating the problem of dynamic adaptation in systems consisting of multiple intelligent agents. An essential characteristic of these systems is that the salient knowledge for learning is distributed amongst the agents. As in human communities, effective learning therefore requires cooperation amongst the constituent members. In this paper we detail the role of cooperation in such learning systems and the problems introduced by it. These ideas have been used in MALE (Multi-Agent Learning Environment) from which an illustrative example is shown.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
A. Bond, Chapters 1–5, in Readings in Distributed AI, A. Bond & L. Gasser (Eds.), p67–99, Morgan Kaufmann, San Mateo, 1988.
S. Cammarata, D. McArthur & R. Steeb, Strategies of Cooperation in Distributed Problem Solving, in Proceedings of IJCAI-83, p767–770, University of Amerhurst, August 1983.
J. Carbonell, Learning by Analogy, in R. Michalski, J. Carbonell & T. Mitchell (Eds.), Machine Learning: An AI Approach, Morgan Kaufmann, San Mateo, 1983.
L. Gasser & M. Huhns, Chapter 1, in Distributed AI Vol 2, L. Gasser & M. Huhns (Eds.), p5–20, Pitman, London, 1989.
M. Huhns, Introduction, in Distributed AI, M. Huhns Ed.), p5–12, Pitman, London, 1987.
Y. Kitamura & T. Okumoto, Diffusing Inference: An Inference Method for Distributed Problem Solving and its Property,in this volume.
Y. Kodratoff, Introduction to Machine Learning, Pitman, London, 1988
R. Michalski, Overview of Machine Learning, in R. Michalski, J. Carbonell & T. Mitchell (Eds.), Machine Learning: An AI Approach, p3–25, Morgan Kaufmann, San Mateo, 1983.
T. Mitchell, R. Keller & S. Kedar-Cabelli, Explanation-Based Generalisation: An Unifying View, Machine Learning, Vol 1(2), April 1986.
H. Parunaik, Manufacturing Experience with the Contract Net, in Distributed Al, M. Huhns (Ed.), p285–310, Pitman, London 1987.
R. Riene & R. Michalski, Incremental Learning of Concept Descriptions, in Machine Intelligence Vol 11, J. Hayes, D. Michie & J. Richards (Eds.), p263–288, Morgan Kaufmann, San Mateo, 1987.
J. Rosenschein, M. Ginsberg & M. Genesreth, Cooperation without Communication, in Proceedings of AAAI-86, p51–57, May 1986.
M. Shaw & A. Whinston, Learning and Adaptation in Distributed AI, in Distributed AI Vol 2, L. Gasser & M. Huhns (Eds.), p413–429, Pitman, London, 1989.
S. Sian, Adaptation Based on Cooperative Learning in Multi-Agent Systems, in Proceedings of MAAMAW ‘80, St. Quentin-en-Yvelines, France, August 1990. Also in Decentralized AI Vol 2, Y. Demazeau & J-P. Muller (Eds.), Elsevier Science Pub. B.V, 1991.
S. Sian, Extending Learning to Multiple Agents: Issues and a Model for Multi-Agent Machine Learning, in Proceedings of Fifth ESWL 1991, Y. Kodratoff (Ed.), Lecture Notes in AI Series, Springer-Verlag Pub., 1991.
S. Sian, Learning in Distributed AI Systems,PhD. Thesis, Department of Computing, Imperial College, University of London (forthcoming).
L. Valiant, A Theory of the Learnable, Communications of the ACM, Vol 27 (11), November 1984.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag London Limited
About this paper
Cite this paper
Sian, S.S. (1991). The Role Of Cooperation in Multi-Agent Learning. In: Deen, S.M. (eds) CKBS ’90. Springer, London. https://doi.org/10.1007/978-1-4471-1831-2_9
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1831-2_9
Publisher Name: Springer, London
Print ISBN: 978-3-540-19649-5
Online ISBN: 978-1-4471-1831-2
eBook Packages: Springer Book Archive