Abstract
Although a large number of algorithms have been proposed for generating cooperative behaviors, the question of how to evaluate mutual benefit among them is still open. This study provides a measure for cooperation degree among the reinforcement learning agents. By means of our proposed measure, that is based on information theory, the degree of interaction among agents can be evaluated from the viewpoint of information sharing. Here, we show the availability of this measure through some experiments on “pursuit game”, and evaluate the degree of cooperation among hunters and prey.
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
Balch, T.: Hierarchic Social Entropy: An Information Theoretic Measure of Robot Group Diversity. Autonomous Robotics 8(3), 209–238 (2000)
Gasser, L., Rouquette, N., Hill, R.W., Lieb, J.: Representing and Using Organizational Knowledge in Distributed AI Systems. In: Gasser, L., Huhns, M.H. (eds.) Distributed Artificial Intelligence, vol. 2, pp. 55–78. Morgan Kaufmann, San Francisco (1989)
Levy, R., Rosenschein, J.S.: A Game Theoretic Approach to Distributed Artificial Intelligence and The Pursuit Problem. In: Proceedings of the 3rd European Workshop on Modeling Autonomous Agents in a Multi-Agent World, pp. 129–146 (1992)
Shannon, C.E.: The Mathematical Theory of Communication. University of Illinois Press (1949)
Tan, M.: Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents. In: Proceedings of the 10th International Conference on Machine Learning, pp. 330–337 (1993)
Watkins, C.J.H., Dayan, P.: Technical note: Q-learning. Machine Learning 8, 55–68 (1992)
Parunak, H.V.D., Brueckner, S.: Entropy and Self-Organization in Multi-Agent Systems”. In: Proceedings of fifth International Conference on Autonomous Agents, pp. 124–130 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arai, S., Ishigaki, Y., Hirata, H. (2008). Measurement of Underlying Cooperation in Multiagent Reinforcement Learning. In: Bui, T.D., Ho, T.V., Ha, Q.T. (eds) Intelligent Agents and Multi-Agent Systems. PRIMA 2008. Lecture Notes in Computer Science(), vol 5357. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89674-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-89674-6_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89673-9
Online ISBN: 978-3-540-89674-6
eBook Packages: Computer ScienceComputer Science (R0)