Meta-level reasoning in deliberative agents
Anita Raja, Victor Lesser · 2014
Deliberative agents operating in open environments must make complex real-time decisions on scheduling and coor-dination of domain activities. These decisions are made in the context of limited resources and uncertainty about the outcomes of activities. We describe a reinforcement learn-ing based approach for efficient meta-level reasoning. Em-pirical results showing the effectiveness of meta-level rea-soning in a complex domain are provided. 1.