RUcore: Rutgers University Community Repository
Efficient learning of relational models for sequential decision making
Descriptive
TypeOfResource
Text
TitleInfo
(ID = T-1)
Title
Efficient learning of relational models for sequential decision making
Identifier
ETD_2790
Identifier
(type = hdl)
http://hdl.rutgers.edu/1782.1/rucore10001600001.ETD.000056852
Language
LanguageTerm
(authority = ISO639-2);
(type = code)
eng
Genre
(authority = marcgt)
theses
Subject
(ID = SBJ-1);
(authority = RUETD)
Topic
Computer Science
Subject
(ID = SBJ-2);
(authority = ETD-LCSH)
Topic
Reinforcement learning
Subject
(ID = SBJ-3);
(authority = ETD-LCSH)
Topic
Artificial intelligence--Educational applications
Abstract
(type = abstract)
The exploration-exploitation tradeoff is crucial to reinforcement-learning (RL) agents, and a significant number of sample complexity results have been derived for agents in propositional domains. These results guarantee, with high probability, near-optimal behavior in all but a polynomial number of timesteps in the agent’s lifetime. In this work, we prove similar results for certain relational representations, primarily a class we call “relational action schemas”. These generalized models allow us to specify state transitions in a compact form, for instance describing the effect of picking up a generic block instead of picking up 10 different specific blocks. We present theoretical results on crucial subproblems in action-schema learning using the KWIK framework, which allows us to characterize the sample efficiency of an agent learning these models in a reinforcement-learning setting. These results are extended in an apprenticeship learning paradigm where and agent has access not only to its environment, but also to a teacher that can demonstrate traces of state/action/state sequences. We show that the class of action schemas that are efficiently learnable in this paradigm is strictly larger than those learnable in the online setting. We link the class of efficiently learnable dynamics in the apprenticeship setting to a rich class of models derived from well-known learning frameworks. As an application, we present theoretical and empirical results on learning relational models of web-service descriptions using a dataflow model called a Task Graph to capture the important connections between inputs and outputs of services in a workflow, with experiments constructed using publicly available web services. This application shows that compact relational models can be efficiently learned from limited amounts of basic data. Finally, we present several extensions of the main results in the thesis, including expansions of the languages with Description Logics. We also explore the use of sample-based planners to speed up the computation time of our algorithms.
PhysicalDescription
Form
(authority = gmd)
electronic resource
Extent
ix, 213 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 Thomas J. Walsh
Name
(ID = NAME-1);
(type = personal)
NamePart
(type = family)
Walsh
NamePart
(type = given)
Thomas J.
NamePart
(type = date)
1981-
Role
RoleTerm
(authority = RULIB)
author
DisplayForm
Thomas Walsh
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)
Borgida
NamePart
(type = given)
Alexander
Role
RoleTerm
(authority = RULIB)
internal member
Affiliation
Advisory Committee
DisplayForm
Alexander Borgida
Name
(ID = NAME-4);
(type = personal)
NamePart
(type = family)
Shan
NamePart
(type = given)
Chung-chieh
Role
RoleTerm
(authority = RULIB)
internal member
Affiliation
Advisory Committee
DisplayForm
Chung-chieh Shan
Name
(ID = NAME-5);
(type = personal)
NamePart
(type = family)
Khardon
NamePart
(type = given)
Roni
Role
RoleTerm
(authority = RULIB)
outside member
Affiliation
Advisory Committee
DisplayForm
Roni Khardon
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)
2010
DateOther
(qualifier = exact);
(type = degree)
2010-10
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/T370814H
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
Reason
Permission or license
RightsHolder
(ID = PRH-1);
(type = personal)
Name
FamilyName
Walsh
GivenName
Thomas
Role
Copyright Holder
RightsEvent
(ID = RE-1);
(AUTHORITY = rulib)
Type
Permission or license
DateTime
2010-07-27 03:06:33
AssociatedEntity
(ID = AE-1);
(AUTHORITY = rulib)
Role
Copyright holder
Name
Thomas Walsh
Affiliation
Rutgers University. Graduate School - New Brunswick
AssociatedObject
(ID = AO-1);
(AUTHORITY = rulib)
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
ContentModel
ETD
MimeType
(TYPE = file)
application/pdf
MimeType
(TYPE = container)
application/x-tar
FileSize
(UNIT = bytes)
1904640
Checksum
(METHOD = SHA1)
f93ba5d9f95e84b58925400640693e1f5e15ac2c
Back to the top
Statistical Profile