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.
0800: Artificial intelligence
0984: Computer science
Identifier / keyword
Applied sciences, Autonomous agents, Behavior hierarchy, Intrinsic motivation, Reinforcement learning, Skill acquisition, Temporal abstraction
Behavioral building blocks for autonomous agents: Description, identification, and learning
DAI-B 69/12, Dissertation Abstracts International
Place of publication
Country of publication
Barto, Andrew G.; Jensen, David; Littman, Michael; Mahadevan, Sridhar; Nahmod, Andrea R.
University of Massachusetts Amherst
United States -- Massachusetts
Dissertations & Theses
ProQuest document ID
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.