For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Maintaining System State Information in a Multiagent Environment for Effective Learning
Gang CHEN Zhonghua YANG Hao HE Kiah-Mok GOH
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/01/01
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Distributed Cooperation and Agents
multiagent system, system state, distributed protocol, token ring,
Full Text: PDF(537KB)>>
One fundamental issue in multiagent reinforcement learning is how to deal with the limited local knowledge of an agent in order to achieve effective learning. In this paper, we argue that this issue can be more effectively solved if agents are equipped with a consistent global view. We achieve this by requiring agents to follow an interacting protocol. The properties of the protocol are derived and theoretically analyzed. A distributed protocol that satisfies these properties is presented. The experimental evaluations are conducted for a well-known test-case (i.e., pursuit game) in the context of two learning algorithms. The results show that the protocol is effective and the reinforcement learning algorithms using it perform much better.