From Infinite to Finite Programs : Explicit Error Bounds with Applications to Approximate Dynamic Programming

Mohajerin Esfahani, Peyman; Sutter, Tobias; Kuhn, Daniel; Lygeros, John

From Infinite to Finite Programs : Explicit Error Bounds with Applications to Approximate Dynamic Programming

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2018

Autor:innen

Mohajerin Esfahani, Peyman

Sutter, Tobias

Kuhn, Daniel

Lygeros, John

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

SIAM Journal on Optimization ; 28 (2018), 3. - S. 1968-1998. - Society for Industrial and Applied Mathematics (SIAM). - ISSN 1052-6234. - eISSN 1095-7189

Zusammenfassung

We consider linear programming (LP) problems in infinite dimensional spaces that are in general computationally intractable. Under suitable assumptions, we develop an approximation bridge from the infinite dimensional LP to tractable finite convex programs in which the performance of the approximation is quantified explicitly. To this end, we adopt the recent developments in two areas of randomized optimization and first-order methods, leading to a priori as well as a posteriori performance guarantees. We illustrate the generality and implications of our theoretical results in the special case of the long-run average cost and discounted cost optimal control problems in the context of Markov decision processes on Borel spaces. The applicability of the theoretical results is demonstrated through a fisheries management problem.

Fachgebiet (DDC)

004 Informatik

Zitieren

ISO 690

MOHAJERIN ESFAHANI, Peyman, Tobias SUTTER, Daniel KUHN, John LYGEROS, 2018. From Infinite to Finite Programs : Explicit Error Bounds with Applications to Approximate Dynamic Programming. In: SIAM Journal on Optimization. Society for Industrial and Applied Mathematics (SIAM). 28(3), pp. 1968-1998. ISSN 1052-6234. eISSN 1095-7189. Available under: doi: 10.1137/17M1133087

BibTex

@article{MohajerinEsfahani2018Infin-55608,
  year={2018},
  doi={10.1137/17M1133087},
  title={From Infinite to Finite Programs : Explicit Error Bounds with Applications to Approximate Dynamic Programming},
  number={3},
  volume={28},
  issn={1052-6234},
  journal={SIAM Journal on Optimization},
  pages={1968--1998},
  author={Mohajerin Esfahani, Peyman and Sutter, Tobias and Kuhn, Daniel and Lygeros, John}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/55608">
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/55608"/>
    <dc:contributor>Sutter, Tobias</dc:contributor>
    <dc:language>eng</dc:language>
    <dcterms:abstract xml:lang="eng">We consider linear programming (LP) problems in infinite dimensional spaces that are in general computationally intractable. Under suitable assumptions, we develop an approximation bridge from the infinite dimensional LP to tractable finite convex programs in which the performance of the approximation is quantified explicitly. To this end, we adopt the recent developments in two areas of randomized optimization and first-order methods, leading to a priori as well as a posteriori performance guarantees. We illustrate the generality and implications of our theoretical results in the special case of the long-run average cost and discounted cost optimal control problems in the context of Markov decision processes on Borel spaces. The applicability of the theoretical results is demonstrated through a fisheries management problem.</dcterms:abstract>
    <dc:creator>Mohajerin Esfahani, Peyman</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-11-22T13:03:42Z</dcterms:available>
    <dc:creator>Kuhn, Daniel</dc:creator>
    <dc:contributor>Lygeros, John</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:issued>2018</dcterms:issued>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Kuhn, Daniel</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-11-22T13:03:42Z</dc:date>
    <dcterms:title>From Infinite to Finite Programs : Explicit Error Bounds with Applications to Approximate Dynamic Programming</dcterms:title>
    <dc:creator>Lygeros, John</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Mohajerin Esfahani, Peyman</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Sutter, Tobias</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Nein

Begutachtet

Ja