RUcore: Rutgers University Community Repository
Probably Approximately Correct (PAC) exploration in reinforcement learning
Descriptive
TitleInfo
(displayLabel = Citation Title);
(type = uniform)
Title
Probably Approximately Correct (PAC) exploration in reinforcement learning
Name
(ID = NAME001);
(type = personal)
NamePart
(type = family)
Strehl
NamePart
(type = given)
Alexander L.
DisplayForm
Alexander L. Strehl
Role
RoleTerm
(authority = RUETD)
author
Name
(ID = NAME002);
(type = personal)
NamePart
(type = family)
Littman
NamePart
(type = given)
Michael
Affiliation
Advisory Committee
DisplayForm
Michael L Littman
Role
RoleTerm
(authority = RULIB)
chair
Name
(ID = NAME003);
(type = personal)
NamePart
(type = family)
Hirsh
NamePart
(type = given)
Haym
Affiliation
Advisory Committee
DisplayForm
Haym Hirsh
Role
RoleTerm
(authority = RULIB)
internal member
Name
(ID = NAME004);
(type = personal)
NamePart
(type = family)
Szegedy
NamePart
(type = given)
Mario
Affiliation
Advisory Committee
DisplayForm
Mario Szegedy
Role
RoleTerm
(authority = RULIB)
internal member
Name
(ID = NAME005);
(type = personal)
NamePart
(type = family)
Kearns
NamePart
(type = given)
Michael
Affiliation
Advisory Committee
DisplayForm
Michael Kearns
Role
RoleTerm
(authority = RULIB)
outside member
Name
(ID = NAME006);
(type = corporate)
NamePart
Rutgers University
Role
RoleTerm
(authority = RULIB)
degree grantor
Name
(ID = NAME007);
(type = corporate)
NamePart
Graduate School - New Brunswick
Role
RoleTerm
(authority = RULIB)
school
TypeOfResource
Text
Genre
(authority = marcgt)
theses
OriginInfo
DateCreated
(qualifier = exact)
2007
DateOther
(qualifier = exact);
(type = degree)
2007
Language
LanguageTerm
English
PhysicalDescription
Form
(authority = marcform)
electronic
InternetMediaType
application/pdf
InternetMediaType
text/xml
Extent
viii, 137 pages
Abstract
Reinforcement Learning (RL) in finite state and action Markov Decision Processes is studied with an emphasis on the well-studied exploration problem. We provide a general RL framework that applies to all results in this thesis and to other results in RL that generalize the finite MDP assumption. We present two new versions of the Model-Based Interval Estimation (MBIE) algorithm and prove that they are both PAC-MDP. These algorithms are provably more efficient any than previously studied RL algorithms. We prove that many model-based algorithms (including R-MAX and MBIE) can be modified so that their worst-case per-step computational complexity is vastly improved without sacrificing their attractive theoretical guarantees. We show that it is possible to obtain PAC-MDP bounds with a model-free algorithm called Delayed Q-learning.
Note
(type = degree)
Ph.D.
Note
(type = bibliography)
Includes bibliographical references (p. 133-136).
Subject
(ID = SUBJ1);
(authority = RUETD)
Topic
Computer Science
Subject
(ID = SUBJ2);
(authority = ETD-LCSH)
Topic
Learning models (Stochastic processes)
Subject
(ID = SUBJ3);
(authority = ETD-LCSH)
Topic
Learning--Mathematical models
Subject
(ID = SUBJ4);
(authority = ETD-LCSH)
Topic
Machine learning
RelatedItem
(type = host)
TitleInfo
Title
Graduate School - New Brunswick Electronic Theses and Dissertations
Identifier
(type = local)
rucore19991600001
Identifier
(type = hdl)
http://hdl.rutgers.edu/1782.2/rucore10001600001.ETD.16785
Identifier
ETD_462
Location
PhysicalLocation
(authority = marcorg);
(displayLabel = Rutgers, The State University of New Jersey)
NjNbRU
Identifier
(type = doi)
doi:10.7282/T3Z3202G
Genre
(authority = ExL-Esploro)
ETD doctoral
Back to the top
Rights
RightsDeclaration
(AUTHORITY = GS);
(ID = rulibRdec0006)
The author owns the copyright to this work.
Copyright
Status
Copyright protected
Availability
Status
Open
AssociatedEntity
(AUTHORITY = rulib);
(ID = 1)
Name
Alexander Strehl
Role
Copyright holder
Affiliation
Rutgers University. Graduate School - New Brunswick
RightsEvent
(AUTHORITY = rulib);
(ID = 1)
Type
Permission or license
Detail
Non-exclusive ETD license
AssociatedObject
(AUTHORITY = rulib);
(ID = 1)
Type
License
Name
Author Agreement License
Detail
I hereby grant to the Rutgers University Libraries and to my school the non-exclusive right to archive, reproduce and distribute my thesis or dissertation, in whole or in part, and/or my abstract, in whole or in part, in and from an electronic format, subject to the release date subsequently stipulated in this submittal form and approved by my school. I represent and stipulate that the thesis or dissertation and its abstract are my original work, that they do not infringe or violate any rights of others, and that I make these grants as the sole owner of the rights to my thesis or dissertation and its abstract. I represent that I have obtained written permissions, when necessary, from the owner(s) of each third party copyrighted matter to be included in my thesis or dissertation and will supply copies of such upon request by my school. I acknowledge that RU ETD and my school will not distribute my thesis or dissertation or its abstract if, in their reasonable judgment, they believe all such rights have not been secured. I acknowledge that I retain ownership rights to the copyright of my work. I also retain the right to use all or part of this thesis or dissertation in future works, such as articles or books.
Back to the top
Technical
Format
(TYPE = mime);
(VERSION = )
application/x-tar
FileSize
(UNIT = bytes)
638976
Checksum
(METHOD = SHA1)
b036fab831c6e98f58884ed770955724e5026b28
ContentModel
ETD
CompressionScheme
other
OperatingSystem
(VERSION = 5.1)
windows xp
Format
(TYPE = mime);
(VERSION = NULL)
application/x-tar
Back to the top
Statistical Profile