Title :
Meta-level reasoning in deliberative agents
Author :
Raja, Anita ; Lesser, Victor
Author_Institution :
Dept. of Software & Inf. Syst., North Carolina Univ., Charlotte, NC, USA
Abstract :
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.
Keywords :
decision making; inference mechanisms; learning (artificial intelligence); multi-agent systems; scheduling; software agents; complex real-time decisions; deliberative agents; domain activities; metalevel reasoning; open environments; reinforcement learning; scheduling; Computer science; Control systems; Costs; Decision making; Information systems; Learning; Monitoring; Multiagent systems; Software systems; Uncertainty;
Conference_Titel :
Intelligent Agent Technology, 2004. (IAT 2004). Proceedings. IEEE/WIC/ACM International Conference on
Print_ISBN :
0-7695-2101-0
DOI :
10.1109/IAT.2004.1342936
