Abstract
In this paper we present a method for extending the capabilities of a reactive agent using learning. The method relies on the emergence of more global behavior from the interaction of smaller behavioral units. To coordinate behaviors we use a dynamic self-organizing feature map and reinforcement learning. The dynamic self-organizing map is used to partition the space of sequences of situations into different regions. Reinforcement learning refines the content of the regions based on the experience of the agent. We show the effectiveness of the method and evaluate it through several simulation studies.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
M. S. Hamdi and K. Kaiser, ‘Adaptable local level arbitration of behaviors’, in Proceedings of The First International Conference on Autonomous Agents, Agents’97, Marina del Rey, CA, USA, (Febuary 1997).
M. S. Hamdi and K. Kaiser, ‘Adaptable arbitration of behaviors: Some simulation results’, Journal of Intelligent Manufacturing, 9 (2), 161–166, (April 1998).
M. S. Hamdi and K. Kaiser, ‘Improving behavior arbitration using exploration and dynamic programming’, in Proceedings of the 11th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Benicàssim, Castellón, Spain, (June 1998).
T. Kohonen, Self-Organization and Associative Memory, Springer Series in Information Sciences 8, Heidelberg, Springer Verlag, 1984.
Richard S. Sutton, ‘Reinforcement learning architectures for animats’, in Proceedings of the First International Conference on Simulation of Adaptive Behavior, eds., Jean-Arcady Meyer and Stewart W. Wilson, Cambridge, MA, (1990). MIT Press.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hamdi, M.S., Kaiser, K. (1998). Learning intelligent behavior. In: Antoniou, G., Slaney, J. (eds) Advanced Topics in Artificial Intelligence. AI 1998. Lecture Notes in Computer Science, vol 1502. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0095048
Download citation
DOI: https://doi.org/10.1007/BFb0095048
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65138-3
Online ISBN: 978-3-540-49561-1
eBook Packages: Springer Book Archive