Geodesic
Stochastic control optimal in the Kullback sense
Kybernetika, Tome 44 (2008) no. 1, pp. 53-60 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

The paper solves the problem of minimization of the Kullback divergence between a partially known and a completely known probability distribution. It considers two probability distributions of a random vector $(u_1, x_1, \ldots, u_T, x_T )$ on a sample space of $2T$ dimensions. One of the distributions is known, the other is known only partially. Namely, only the conditional probability distributions of $x_\tau$ given $u_1, x_1, \ldots, u_{\tau-1}, x_{\tau-1}, u_{\tau}$ are known for $\tau = 1, \ldots, T$. Our objective is to determine the remaining conditional probability distributions of $u_\tau$ given $u_1, x_1, \ldots, u_{\tau-1}, x_{\tau-1}$ such that the Kullback divergence of the partially known distribution with respect to the completely known distribution is minimal. Explicit solution of this problem has been found previously for Markovian systems in Karný [Karny:96a]. The general solution is given in this paper.
The paper solves the problem of minimization of the Kullback divergence between a partially known and a completely known probability distribution. It considers two probability distributions of a random vector $(u_1, x_1, \ldots, u_T, x_T )$ on a sample space of $2T$ dimensions. One of the distributions is known, the other is known only partially. Namely, only the conditional probability distributions of $x_\tau$ given $u_1, x_1, \ldots, u_{\tau-1}, x_{\tau-1}, u_{\tau}$ are known for $\tau = 1, \ldots, T$. Our objective is to determine the remaining conditional probability distributions of $u_\tau$ given $u_1, x_1, \ldots, u_{\tau-1}, x_{\tau-1}$ such that the Kullback divergence of the partially known distribution with respect to the completely known distribution is minimal. Explicit solution of this problem has been found previously for Markovian systems in Karný [Karny:96a]. The general solution is given in this paper.
Classification : 49N35, 60G35, 90D60, 91A60, 93E03, 93E20, 94A17
Keywords: Kullback divergence; minimization; stochastic controller 
@article{KYB_2008_44_1_a4,
     author = {\v{S}indel\'a\v{r}, Jan and Vajda, Igor and K\'arn\'y, Miroslav},
     title = {Stochastic control optimal in the {Kullback} sense},
     journal = {Kybernetika},
     pages = {53--60},
     year = {2008},
     volume = {44},
     number = {1},
     mrnumber = {2405055},
     zbl = {1145.93053},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_2008_44_1_a4/}
}
TY  - JOUR
AU  - Šindelář, Jan
AU  - Vajda, Igor
AU  - Kárný, Miroslav
TI  - Stochastic control optimal in the Kullback sense
JO  - Kybernetika
PY  - 2008
SP  - 53
EP  - 60
VL  - 44
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/KYB_2008_44_1_a4/
LA  - en
ID  - KYB_2008_44_1_a4
ER  - 
%0 Journal Article
%A Šindelář, Jan
%A Vajda, Igor
%A Kárný, Miroslav
%T Stochastic control optimal in the Kullback sense
%J Kybernetika
%D 2008
%P 53-60
%V 44
%N 1
%U http://geodesic.mathdoc.fr/item/KYB_2008_44_1_a4/
%G en
%F KYB_2008_44_1_a4
Šindelář, Jan; Vajda, Igor; Kárný, Miroslav. Stochastic control optimal in the Kullback sense. Kybernetika, Tome 44 (2008) no. 1, pp. 53-60. http://geodesic.mathdoc.fr/item/KYB_2008_44_1_a4/

[1] Aoki M.: Optimization of Stochastic Systems: Topics in Discrete-Time Systems. Academic Press, New York – London 1967 | MR | Zbl

[2] Åström K. J.: Introduction to Stochastic Control. Academic Press, New York – San Francisco – London 1970 | Zbl

[3] Bertsekas D. P.: Dynamic Programming and Stochastic Control. Second edition. Athena Scientific, Belmont, Mass. 2000 | MR | Zbl

[4] Clark D.: Advances in Model-Based Predictive Control. Oxford University Press, Oxford 1994

[5] Cover T. M., Thomas J. A.: Elements of Information Theory. Second edition. Wiley-Interscience, New York 2006 | MR | Zbl

[6] Kárný M.: Towards fully probabilistic control design. Automatica 32 (1996), 12, 1719–1722 | MR | Zbl

[7] Kulhavý R.: A Kullback–Leibler distance approach to system identification. In: Preprints of the IFAC Symposium on Adaptive Systems in Control and Signal Processing (C. Bányász, ed.), Budapest 1995, pp. 55–66

[8] Kullback S.: Information Theory and Statistics. Wiley, New York and Chapman & Hall, London 1967 | MR | Zbl

[9] Kullback S., Leibler R.: On information and sufficiency. Ann. Math. Statist. 22 (1951), 79–87 | MR | Zbl

[10] Kumar P. R., Varaiya P.: Stochastic Systems: Estimation, Identification and Adaptive Control. Prentice Hall, Englewood Cliffs, N. J. 1986 | Zbl

[11] Kushner H.: Introduction to Stochastic Control. Holt, Rinehard and Winston, New York 1971 | MR | Zbl

[12] Martin J. J.: Bayesian Decision Problems and Markov Chains. Wiley, New York 1967 | MR | Zbl

[13] Meditch J. S.: Stochastic Optimal Linear Estimation and Control. Mc. Graw Hill, New York 1969 | Zbl

[14] Vajda I.: Theory of Statistical Inference and Information. Mathematical and statistical methods. Kluwer Academic Publishers, Dordrecht, Boston – London 1989 | Zbl