Number of the records: 1

Fully probabilistic control design in an adaptive critic framework

SYSNO ASEP	0364820
Document Type	J - Journal Article
R&D Document Type	Journal Article
Subsidiary J	Článek ve WOS
Title	Fully probabilistic control design in an adaptive critic framework
Author(s)	Herzallah, R. (JO) Kárný, Miroslav (UTIA-B)_{RID, ORCID}
Source Title	Neural Networks. - : Elsevier - ISSN 0893-6080 Roč. 24, č. 10 (2011), s. 1128-1135
Number of pages	8 s.
Language	eng - English
Country	GB - United Kingdom
Keywords	Stochastic control design ; Fully probabilistic design ; Adaptive control ; Adaptive critic
Subject RIV	BC - Control Systems Theory
R&D Projects	GA102/08/0567 GA ČR - Czech Science Foundation (CSF)
CEZ	AV0Z10750506 - UTIA-B (2005-2011)
UT WOS	000297000300012
EID SCOPUS	80054779788
DOI	10.1016/j.neunet.2011.06.006
Annotation	Optimal stochastic controller pushes the closed-loop behavior as close as possible to the desired one. The fully probabilistic design (FPD) uses probabilistic description of the desired closed loop and minimizes Kullback–Leibler divergence of the closed-loop description to the desired one. Practical exploitation of the fully probabilistic design control theory continues to be hindered by the computational complexities involved in numerically solving the associated stochastic dynamic programming problem; in particular, very hard multivariate integration and an approximate interpolation of the involved multivariate functions. This paper proposes a new fully probabilistic control algorithm that uses the adaptive critic methods to circumvent the need for explicitly evaluating the optimal value function, thereby dramatically reducing computational requirements. This is a main contribution of this paper.
Workplace	Institute of Information Theory and Automation
Contact	Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
Year of Publishing	2012

Number of the records: 1