eprintid: 1035
rev_number: 7
eprint_status: archive
userid: 6
dir: disk0/00/00/10/35
datestamp: 2011-12-06 10:51:35
lastmod: 2011-12-06 10:51:35
status_changed: 2011-12-06 10:51:35
type: conference_item
metadata_visibility: show
creators_name: Patrinos, Panagiotis
creators_name: Sarimveis, Haralambos
creators_id: panagiotis.patrinos@imtlucca.it
creators_id: 
title: An RBF based neuro-dynamic approach for the control of stochastic dynamic systems
ispublished: pub
subjects: QA
subjects: TJ
divisions: CSA
full_text_status: none
pres_type: paper
abstract: This paper presents a neuro-dynamic programming methodology for the control of markov decision processes. The proposed method can be considered as a variant of the optimistic policy iteration, where radial basis function (RBF) networks are employed as a compact representation of the cost-to-go function and the ॕ-LSPE is used for policy evaluation. We also emphasize the reformulation of the Bellman equation around the post-decision state in order to circumvent the calculation of the expectation. The proposed algorithm is applied to a retailer-inventory management problem.
date: 2005
event_title: 16th IFAC World Congress
event_location: Prague, Czech Republic
event_dates: 3-8 July 2005
event_type: conference
refereed: TRUE
official_url: http://www.ifac-papersonline.net/Detailed/28368.html
citation:   Patrinos, Panagiotis and Sarimveis, Haralambos  An RBF based neuro-dynamic approach for the control of stochastic dynamic systems.  In: 16th IFAC World Congress, 3-8 July 2005, Prague, Czech Republic         (2005)