Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case

We study the behavior of the rolling horizon procedure for semi-Markov decision processes, with infinite-horizon discounted reward, when the state space is a Borel set and the action spaces are considered compact. We prove the convergence of the rewards produced by the rolling horizon policies to th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Vecchia, Eugenio Della, Di Marco, Silvia, Jean-Marie, Alain
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2011
Materias:	Ciencias Informáticas Semi-Markov decision processes Rolling horizon Discounted criterion
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/139314 https://40jaiio.sadio.org.ar/sites/default/files/T2011/SIO/701.pdf
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-139314
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Semi-Markov decision processes Rolling horizon Discounted criterion
spellingShingle	Ciencias Informáticas Semi-Markov decision processes Rolling horizon Discounted criterion Vecchia, Eugenio Della Di Marco, Silvia Jean-Marie, Alain Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
topic_facet	Ciencias Informáticas Semi-Markov decision processes Rolling horizon Discounted criterion
description	We study the behavior of the rolling horizon procedure for semi-Markov decision processes, with infinite-horizon discounted reward, when the state space is a Borel set and the action spaces are considered compact. We prove the convergence of the rewards produced by the rolling horizon policies to the optimal reward function, when the horizon length tends to infinity, under different assumptions on the instantaneous reward function. The approach is based on extensions of the results obtained in [7] for the discrete-time Markov decision process case and in [3] for the case of discrete-time Markov games. Finally, we also analyse the performance of an approximate rolling horizon procedure.
format	Objeto de conferencia Objeto de conferencia
author	Vecchia, Eugenio Della Di Marco, Silvia Jean-Marie, Alain
author_facet	Vecchia, Eugenio Della Di Marco, Silvia Jean-Marie, Alain
author_sort	Vecchia, Eugenio Della
title	Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
title_short	Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
title_full	Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
title_fullStr	Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
title_full_unstemmed	Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
title_sort	rolling horizon procedure on controlled semi-markov models. the discounted case
publishDate	2011
url	http://sedici.unlp.edu.ar/handle/10915/139314 https://40jaiio.sadio.org.ar/sites/default/files/T2011/SIO/701.pdf
work_keys_str_mv	AT vecchiaeugeniodella rollinghorizonprocedureoncontrolledsemimarkovmodelsthediscountedcase AT dimarcosilvia rollinghorizonprocedureoncontrolledsemimarkovmodelsthediscountedcase AT jeanmariealain rollinghorizonprocedureoncontrolledsemimarkovmodelsthediscountedcase
bdutipo_str	Repositorios
_version_	1764820457484189696

Rolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case

Ejemplares similares