Model based Exploration in Continuous State Spaces
RUcore: Rutgers University Community Repository
Efficient model-based exploration in continuous state-space environments
Descriptive
TitleInfo (ID = T-1)
Title
Efficient model-based exploration in continuous state-space environments
Identifier (type = hdl)
http://hdl.rutgers.edu/1782.1/rucore10001600001.ETD.000057652
Language
LanguageTerm (authority = ISO639-2); (type = code)
eng
Genre (authority = marcgt)
theses
Subject (ID = SBJ-1); (authority = RUETD)
Subject (ID = SBJ-2); (authority = ETD-LCSH)
Subject (ID = SBJ-3); (authority = ETD-LCSH)
Topic
Reinforcement learning--Methodology
Subject (ID = SBJ-4); (authority = ETD-LCSH)
Abstract (type = abstract)
The impetus for exploration in reinforcement learning (RL) is decreasing uncertainty about the environment for the purpose of better decision making. As such, exploration plays a crucial role in the efficiency of RL algorithms. In this dissertation, I consider continuous state control problems and introduce a new methodology for representing uncertainty that engenders more efficient algorithms. I argue that the new notion of uncertainty allows for more efficient use of function approximation, which is essential for learning in continuous spaces. In particular, I focus on a class of algorithms referred to as model-based methods and develop several such algorithms that are much more efficient than the current state-of-the-art methods. These algorithms attack the long-standing "curse of dimensionality''--- learning complexity often scales exponentially with problem dimensionality. I introduce algorithms that can exploit the dependency structure between state variables to exponentially decrease the sample complexity of learning, both in cases where the dependency structure is provided by the user a priori and cases where the algorithm has to find it on its own. I also use the new uncertainty notion to derive a multi-resolution exploration scheme, and demonstrate how this new technique achieves anytime behavior, which is very important in real-life applications. Finally, using a set of rich experiments, I show how the new exploration mechanisms affect the efficiency of learning, especially in real-life domains where acquiring samples is expensive.
PhysicalDescription
Form (authority = gmd)
electronic resource
Extent
xiv, 169 p. : ill.
InternetMediaType
application/pdf
InternetMediaType
text/xml
Note (type = degree)
Ph.D.
Note (type = bibliography)
Includes bibliographical references
Note (type = vita)
Includes vita
Note (type = statement of responsibility)
by Ali Nouri
Name (ID = NAME-1); (type = personal)
NamePart (type = family)
Nouri
NamePart (type = given)
Ali
NamePart (type = date)
1980-
Role
RoleTerm (authority = RULIB)
author
Name (ID = NAME-2); (type = personal)
NamePart (type = family)
Littman
NamePart (type = given)
Michael L.
Role
RoleTerm (authority = RULIB)
chair
Affiliation
Advisory Committee
DisplayForm
Michael L. Littman
Name (ID = NAME-3); (type = personal)
NamePart (type = family)
Kulikowski
NamePart (type = given)
Casimir
Role
RoleTerm (authority = RULIB)
internal member
Affiliation
Advisory Committee
DisplayForm
Casimir Kulikowski
Name (ID = NAME-4); (type = personal)
NamePart (type = family)
Pavlovic
NamePart (type = given)
Vladimir
Role
RoleTerm (authority = RULIB)
internal member
Affiliation
Advisory Committee
DisplayForm
Vladimir Pavlovic
Name (ID = NAME-5); (type = personal)
NamePart (type = family)
Precup
NamePart (type = given)
Doina
Role
RoleTerm (authority = RULIB)
outside member
Affiliation
Advisory Committee
Name (ID = NAME-1); (type = corporate)
NamePart
Rutgers University
Role
RoleTerm (authority = RULIB)
degree grantor
Name (ID = NAME-2); (type = corporate)
NamePart
Graduate School - New Brunswick
Role
RoleTerm (authority = RULIB)
school
OriginInfo
DateCreated (qualifier = exact)
2011
DateOther (qualifier = exact); (type = degree)
2011-01
Place
PlaceTerm (type = code)
xx
RelatedItem (type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
Identifier (type = RULIB)
ETD
RelatedItem (type = host)
TitleInfo
Title
Graduate School - New Brunswick Electronic Theses and Dissertations
Identifier (type = local)
rucore19991600001
Location
PhysicalLocation (authority = marcorg); (displayLabel = Rutgers, The State University of New Jersey)
NjNbRU
Identifier (type = doi)
doi:10.7282/T35D8RG6
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
Reason
Permission or license
RightsHolder (ID = PRH-1); (type = personal)
RightsEvent (ID = RE-1); (AUTHORITY = rulib)
Type
Permission or license
DateTime
2011-01-06 12:30:18
AssociatedEntity (ID = AE-1); (AUTHORITY = rulib)
Affiliation
Rutgers University. Graduate School - New Brunswick
AssociatedObject (ID = AO-1); (AUTHORITY = rulib)
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
MimeType (TYPE = file)
application/pdf
MimeType (TYPE = container)
application/x-tar
FileSize (UNIT = bytes)
13936640
Checksum (METHOD = SHA1)
891331948787d890a993999d3fac70e591a338c1
Back to the top
Source: https://rucore.libraries.rutgers.edu/rutgers-lib/31145/record/
0 Response to "Model based Exploration in Continuous State Spaces"
Post a Comment