Abstract/Details

Behavioral building blocks for autonomous agents: Description, identification, and learning


2008 2008

Other formats: Order a copy

Abstract (summary)

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.

Indexing (details)


Subject
Artificial intelligence;
Computer science
Classification
0800: Artificial intelligence
0984: Computer science
Identifier / keyword
Applied sciences; Autonomous agents; Behavior hierarchy; Intrinsic motivation; Reinforcement learning; Skill acquisition; Temporal abstraction
Title
Behavioral building blocks for autonomous agents: Description, identification, and learning
Author
Simsek, Ozgur
Number of pages
110
Publication year
2008
Degree date
2008
School code
0118
Source
DAI-B 69/12, Dissertation Abstracts International
Place of publication
Ann Arbor
Country of publication
United States
ISBN
9780549916222
Advisor
Barto, Andrew G.
Committee member
Barto, Andrew G.; Jensen, David; Littman, Michael; Mahadevan, Sridhar; Nahmod, Andrea R.
University/institution
University of Massachusetts Amherst
Department
Computer Science
University location
United States -- Massachusetts
Degree
Ph.D.
Source type
Dissertations & Theses
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
3337035
ProQuest document ID
304566700
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Document URL
http://search.proquest.com/docview/304566700
Access the complete full text

You can get the full text of this document if it is part of your institution's ProQuest subscription.

Try one of the following:

  • Connect to ProQuest through your library network and search for the document from there.
  • Request the document from your library.
  • Go to the ProQuest login page and enter a ProQuest or My Research username / password.