Kapetanakis, S. and Kudenko, D. (2002) Reinforcement Learning of Coordination in Cooperative Multi-Agent Systems. In: Dechter, R., Kearns, M. and Sutton, R., (eds.) Proceedings of the 18th National Conference on Artificial Intelligence (AAAI). AAAI-02, July 28 – August 1, 2002, Edmonton, Alberta, Canada. , pp. 326-331. ISBN 978-0-262-51129-2
Abstract
We report on an investigation of reinforcement learning techniques for the learning of coordination in cooperative multi-agent systems. Specifically, we focus on a novel action selection strategy for Q-learning. The new technique is applicable to scenarios where mutual observation of actions is not possible. To date, reinforcement learning approaches for such independent agents did not guarantee convergence to the optimal joint action in scenarios with high miscoordination costs. We improve on previous results by demonstrating empirically that our extension causes the agents to converge almost always to the optimal joint action even in these difficult cases.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | York RAE Import |
Date Deposited: | 07 Apr 2009 09:56 |
Last Modified: | 07 Apr 2009 09:56 |
Status: | Published |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:7312 |