Fully probabilistic control design in an adaptive critic framework
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F11%3A00364820" target="_blank" >RIV/67985556:_____/11:00364820 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1016/j.neunet.2011.06.006" target="_blank" >http://dx.doi.org/10.1016/j.neunet.2011.06.006</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.neunet.2011.06.006" target="_blank" >10.1016/j.neunet.2011.06.006</a>
Alternative languages
Result language
angličtina
Original language name
Fully probabilistic control design in an adaptive critic framework
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
BC - Theory and management systems
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA102%2F08%2F0567" target="_blank" >GA102/08/0567: Fully probabilistic design of dynamic decision strategies</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Neural Networks
ISSN
0893-6080
e-ISSN
—
Volume of the periodical
24
Issue of the periodical within the volume
10
Country of publishing house
GB - UNITED KINGDOM
Number of pages
8
Pages from-to
1128-1135
UT code for WoS article
000297000300012
EID of the result in the Scopus database
—