Developing collaborative Golog agents by reinforcement learning

 
EPrints.org
Agentlink Clearinghouse is powered by GNU EPrints developed by the School of Electronics and Computer Science of the University of Southampton.
Type: Article

Letia, Ioan Alfred and Precup, Doina (2002) Developing collaborative Golog agents by reinforcement learning. International Journal on Artificial Intelligence Tools, 11 (2). pp. 233-246. ISSN 0218-2130

Full text not available from this archive.

Abstract

We consider applications where agents have to cooperate without any communication taking place between them, apart from the fact that they can see part of the environment in which they act. We present a multi-agent system, defined in Golog, that needs to service tasks whose value degrades in time. Initial plans, reflecting prior knowledge about the environment, are expressed as Golog procedures, and are provided to the agents. Then the agents are trained using reinforcement learning, in order to ensure coordination both at the action level and at the plan level. This ensures better scalabilityand increased performance of the system.

Deposited by professor Ioan Alfred Letia on 14 July 2005

Archive Staff Only: edit this record

   

AgentLink is the European Commission's IST-funded Coordination Action for Agent-Based Computing
and is coordinated by the
University of Liverpool and University of Southampton
If you encounter any problems with these pages please contact web@agentlink.org.