A Multistrategy Learning Scheme for Assimilating Advice in Embedded Agents

Abstract

The problem of designing and refining tasklevel strategies in an embedded multiagent setting is an important unsolved question. To address this problem, we have developed a multistrategy system that combines two learning methods: operationalization of high-level advice provided by a human and incremental refinement by a genetic algorithm. The first method generates seed rules for finer-grained refinements by the genetic algorithm. Our multistrategy learning system is evaluated on two complex simulated domains as well as with a Nomad 200 robot. Key words: advice, operationalize, genetic algorithms 1 Introduction The problem of designing and refining tasklevel strategies in an embedded multi-agent setting is an important unsolved question. To address this problem, we have developed a multistrategy learning system that combines two learning methods: operationalization of high-level advice provided by a human, and incremental refinement by a genetic algorithm (GA). We define advice as a ...