dc.creatorVecchia, Eugenio Della
dc.creatorDi Marco, Silvia
dc.creatorJean-Marie, Alain
dc.date2011-08
dc.date2011
dc.date2022-07-12T12:15:49Z
dc.date.accessioned2023-07-15T07:25:50Z
dc.date.available2023-07-15T07:25:50Z
dc.identifierhttp://sedici.unlp.edu.ar/handle/10915/139314
dc.identifierhttps://40jaiio.sadio.org.ar/sites/default/files/T2011/SIO/701.pdf
dc.identifierissn:1850-2865
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/7480459
dc.descriptionWe 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.
dc.descriptionSociedad Argentina de Informática e Investigación Operativa
dc.formatapplication/pdf
dc.format25-37
dc.languageen
dc.rightshttp://creativecommons.org/licenses/by-nc-sa/4.0/
dc.rightsCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.subjectCiencias Informáticas
dc.subjectSemi-Markov decision processes
dc.subjectRolling horizon
dc.subjectDiscounted criterion
dc.titleRolling Horizon Procedure on Controlled Semi-Markov Models. The Discounted Case
dc.typeObjeto de conferencia
dc.typeObjeto de conferencia


Este ítem pertenece a la siguiente institución