Measurement of Underlying Cooperation in Multiagent Reinforcement Learning
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.
KeywordsMutual Information Cooperative Behavior Game Theoretic Approach Pursuit Problem Pursuit Game
Unable to display preview. Download preview PDF.
- 3.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)Google Scholar
- 4.Shannon, C.E.: The Mathematical Theory of Communication. University of Illinois Press (1949)Google Scholar
- 5.Tan, M.: Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents. In: Proceedings of the 10th International Conference on Machine Learning, pp. 330–337 (1993)Google Scholar
- 6.Watkins, C.J.H., Dayan, P.: Technical note: Q-learning. Machine Learning 8, 55–68 (1992)Google Scholar
- 7.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)Google Scholar