Measurement of Underlying Cooperation in Multiagent Reinforcement Learning

Authors:
Sachiyo Arai;Yoshihisa Ishigaki;Hironori Hirata
Affiliations:
Graduate School of Engineering, Chiba University, Chiba, Japan;Graduate School of Engineering, Chiba University, Chiba, Japan;Graduate School of Engineering, Chiba University, Chiba, Japan
Venue:
PRIMA '08 Proceedings of the 11th Pacific Rim International Conference on Multi-Agents: Intelligent Agents and Multi-Agent Systems
Year:
2008

Citing 4
Cited 0

Representing and using organizational knowledge in DAI systems

Distributed Artificial Intelligence (Vol. 2)
Technical Note: \cal Q-Learning

Machine Learning
Entropy and self-organization in multi-agent systems

Proceedings of the fifth international conference on Autonomous agents
Hierarchic Social Entropy: An Information Theoretic Measure of Robot Group Diversity

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

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.