2004 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'04)
Meta-Level Reasoning in Deliberative Agents
Beijing, China
September 20-September 24
ISBN: 0-7695-2101-0
Deliberative agents operating in open environments must make complex real-time decisions on scheduling and coordination of domain activities. These decisions are made in the context of limited resources and uncertainty about the outcomes of activities. We describe a reinforcement learning based approach for efficient meta-level reasoning. Empirical results showing the effectiveness of meta-level reasoning in a complex domain are provided.