Behavioral building blocks for autonomous agents: description, identification, and learning
Andrew G. Barto, Özgür Şimşek · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · 2008
The broad problem I address in this dissertation is design of autonomous agents that can efficiently learn how to achieve desired behaviors in large, complex environments. I focus on one essential design component: the ability to form new behavioral units, or skills, from existing ones. I propose a characterization of a useful class of skills in terms of general properties of an agent's interaction with its environment—in contrast to specific properties of a particular environment—and I introduce methods that can be used to identify and acquire such skills autonomously.