Abstract
In this paper, we are concerned with “organizational learning” in the multiagents systems. As an example for the organizational problem solving process, we will take the task allocation process. The process always enhances the performance of organization, however it is difficult for designers to make the process suitable for the organization and its environment. For that reason, the learning ability is necessary for the process, since it gives them adaptability and robustness. This paper is intend to investigate the relation between selection of task allocation style and its task allocation costs in the learning organization. We introduce an organizational learning model consisting of reinforcement learning agents. These agents learn about ability of other agents in the organization and themselves through their experience of interaction. Thus, we show the results of simulation, and discuss on them.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Cohen, M.D. and Sproull, L.S. eds.: Organizational Learning, Sage Publications, California, 1996.
Gasser, L. and Huhn, M.N. eds.: Distributed Artificial Intelligence II, Morgan Kaufmann, California, 1989.
Malone, T.W.: Modeling Coordination in Organizations and Markets, Management Science, 10, 1987.
Ohko, T., Hiraki, K., and Anzai, Y.: Learning to Reduce Communication Cost on Task Negotiation among Multiple Autonomous Robots, In Sen, S. and Weiss, G. eds., Adaptation and Learning in MultiAgent Systems, pp.177–190, Springer, 1996.
Organizational Science, 2 (1), 1991.
Shaerf, A., Shoham, Y., and Tennenholtz, M.: Adaptive Load Balancing: A Study in Multi-Agent Learning, Journal of Artificial Intelligence Research, 2, pp.450–475, 1995.
Shaw, M.J., and Whinston, A.B.: Learning and Adaptation in Distributed Artificial Intelligence Systems, In Huhn, M.N. and Gasser, L., eds.: Distributed Artificial Intelligence II, pp.119–137, Morgan Kaufmann, California, 1989.
Sikora, R., and Shaw, M.J.: A Computational Study of Distributed Rule Learning, Information Systems Research, 7 (2), pp. 189–197, 1996.
Smith, R.G.: The contract net protocol: High-level communication and control in a distributed problem solver, IEEE Transactions on Computers, C-29 (12), pp.357–366, 1980.
Terano, T.: Learning from Problem Solving and Communication: A Computational Model for Distributed Knowledge Systems, Proc. FGCS'94, Workshop on Heterogeneous Cooperative Knowledge Bases, p.153, 1994.
Watkins, C.J.C.H. and Dyan, P.: Technical Note: Q-Learning, Machine Learning, 8, pp.279–292, 1992.
Weiss, G.: Some Studies in Distributed Machine Learning and Organizational Design, Technical report FKI-189-94 TU Muenchen, 1994.
Weiss, G.: Distributed Machine Learning, Infix, Sankt Augustin, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Terabe, M., Washio, T., Katai, O., Sawaragi, T. (1997). A study of organizational learning in multiagents systems. In: Weiß, G. (eds) Distributed Artificial Intelligence Meets Machine Learning Learning in Multi-Agent Environments. LDAIS LIOME 1996 1996. Lecture Notes in Computer Science, vol 1221. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62934-3_48
Download citation
DOI: https://doi.org/10.1007/3-540-62934-3_48
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62934-4
Online ISBN: 978-3-540-69050-4
eBook Packages: Springer Book Archive