Mostrar el registro sencillo del ítem
dc.contributor.author
Della Vecchia, Eugenio Martín
dc.contributor.author
Di Marco, Silvia Cristina
dc.contributor.author
Jean-marie, Alain
dc.date.available
2023-03-07T12:15:15Z
dc.date.issued
2012-02
dc.identifier.citation
Della Vecchia, Eugenio Martín; Di Marco, Silvia Cristina; Jean-marie, Alain; Illustrated review of convergence conditions of the value iteration algorithm and the rolling horizon procedure for average-cost MDPs; Springer; Annals Of Operations Research; 199; 1; 2-2012; 193-214
dc.identifier.issn
0254-5330
dc.identifier.uri
http://hdl.handle.net/11336/189791
dc.description.abstract
This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon procedure, for solving problems of stochastic optimal control under the long-run average criterion, in Markov Decision Processes with finite state and action spaces. We review conditions of the literature which imply the geometric convergence of Value Iteration to the optimal value. Aperiodicity is an essential prerequisite for convergence. We prove that the convergence of Value Iteration generally implies that of Rolling Horizon. We also present a modified Rolling Horizon procedure that can be applied to models without analyzing periodicity, and discuss the impact of this transformation on convergence. We illustrate with numerous examples the different results. Finally, we discuss rules for stopping Value Iteration or finding the length of a Rolling Horizon. We provide an example which demonstrates the difficulty of the question, disproving in particular a conjectured rule proposed by Puterman.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Springer
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
HEURISTIC METHODS
dc.subject
MARKOV DECISION PROBLEMS
dc.subject
ROLLING HORIZON
dc.subject
VALUE ITERATION
dc.subject.classification
Matemática Aplicada
dc.subject.classification
Matemáticas
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
dc.title
Illustrated review of convergence conditions of the value iteration algorithm and the rolling horizon procedure for average-cost MDPs
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2023-03-07T11:25:48Z
dc.journal.volume
199
dc.journal.number
1
dc.journal.pagination
193-214
dc.journal.pais
Alemania
dc.journal.ciudad
Berlin
dc.description.fil
Fil: Della Vecchia, Eugenio Martín. Universidad Nacional de Rosario; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario; Argentina
dc.description.fil
Fil: Di Marco, Silvia Cristina. Universidad Nacional de Rosario; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario; Argentina
dc.description.fil
Fil: Jean-marie, Alain. No especifíca;
dc.journal.title
Annals Of Operations Research
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://link.springer.com/article/10.1007/s10479-012-1070-0
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1007/s10479-012-1070-0
Archivos asociados