Abstract
In multi-agent systems two forms of learning can be distinguished: centralized learning, that is, learning done by a single agent independent of the other agents; and distributed learning, that is, learning that becomes possible only because several agents are present. Whereas centralized learning has been intensively studied in the field of artificial intelligence, distributed learning has been completely neglected until a few years ago
This paper summarizes work done on distributed reinforcement learning. The problem addressed is how multiple agents can learn to coordinate their actions such that they collectively solve a given environmental task. Two learning algorithms called ACE and DFG are described that provide answers to the following two questions:
-
How can multiple agents learn which actions have to be carried out concurrently?
-
How can multiple agents learn which sets of concurrent actions have to be carried out sequentially? Initial experimental results are provided which illustrate the learning abilities of these algorithms
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
Argyris, C., Schön, D.A.: Organizational learning. Reading, MA: Addisony 1978
Bond, A.H., Gasser, L. (eds.): Readings in distributed artificial intelligence. San Mateo, CA: Morgan Kaufmann 1988
Brauer, W., Hernández, D. (eds.): Verteilte Künstliche Intelligenz und kooperatives Arbeiten. Berlin: Springer-Verag 1991
Brazdil, P., Muggleton, S.: Learning to relate terms in a multiple agent environment. In: Kodratoff, Y. (ed.): Machine learning–EWSL-91. Berlin: Springer-Verlag 1991, pp. 424–439
Galbraith, J.: Designing complex organizations. New York: Wiley 1973
Gasser, L., Huhns, M.N. (eds.): Distributed artificial intelligence (Vol. 2 ). London: Pitman 1989
Ginsberg, M.L.: Possible worlds planning. In: Georgeff, M.P., Lansley, A.L. (eds.): Reasoning about actions and plans — Proceedings of the 1986 workshop. Morgan Kaufmann 1986, pp. 213–243
Goldberg, D.E.: Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley 1989
Grefenstette, J.J.: Credit assignment in rule discovery systems based on genetic algorithms. Machine Learning 3, 225–245 (1988)
Guzzo, R.A.: Improving group decision making in organizations–Approaches from theory and research. Academic Press 1982
Holland, J.H.: Properties of the bucket brigade algorithm. In: Grefenstette, J.J. (ed.), Proceedings of the First International Conference on Genetic Algorithms and Their Applications. Hillsdale, NJ: Lawrence Erlbaum 1985, pp. 1–7
Holland, J.H.: Escaping brittleness: The possibilities of general–purpose learning algorithms to parallel rule–based systems. In: Michalski, R.S., Carbonell, J.G., Mitchell, T.M. (eds.): Machine learning: An artificial intelligence approach (Vol. 2). Morgan Kaufmann 1986, pp. 593–632
Huhns, M. (ed.): Distributed artificial intelligence. London: Pitman 1987
Shaw, M.J., Whinston, A.B.: Learning and adaptation in distributed artificial intelligence. In: ( Gasser fe Huhns, 1989, pp. 413–429 )
Sian, S.S.: Adaptation based on cooperative learning in multi-agent systems. In: Demazeau, Y., Müller J.-P. (eds.): Decentralized AI (Vol. 2 ). Amsterdam: Elsevier 1991
Tan, M.: Multi-agent, reinforcement learning: Independent versus cooperative agents. Proceedings of the Tenth International Conference on Machine Learning. 1993, pp. 330–337
Weiß, G.: Learning the goal relevance of actions in classifier systems. Proceedings of the Tenth European Conference on Artificial Intelligence. Chichester: Wiley 1992, pp. 430–434
Weiß, G.: Learning to coordinate actions in multi-agent systems. Proceedings of the 13th International Joint Conference on Artificial Intelligence. San Mateo, CA: Morgan Kaufmann 1993a, pp. 311–316
Weiß, G.: Action selection and learning in multi-agent environments. Proceedings of the Second International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press 1993b, pp. 502–510
Weiß, G.: Distributed machine learning. Sankt Augustin, Germany: infix Verlag 1995
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weiß, G. (1995). Distributed Reinforcement Learning. In: Steels, L. (eds) The Biology and Technology of Intelligent Autonomous Agents. NATO ASI Series, vol 144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79629-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-79629-6_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-79631-9
Online ISBN: 978-3-642-79629-6
eBook Packages: Springer Book Archive