In this paper we consider the adaptive control of constrained finite ergodic controller Markov chains whose transition probabilities are unknown. The control policy is designed to achieve the minimization of a loss function under a set of inequality constraints. The average values of conditional mat
β¦ LIBER β¦
On the value function in constrained control of Markov chains
β Scribed by Eitan Altman; Arie Hordijk; Lodewijk C. M. Kallenberg
- Publisher
- Springer
- Year
- 1996
- Tongue
- English
- Weight
- 648 KB
- Volume
- 44
- Category
- Article
- ISSN
- 0340-9422
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Penalty function and adaptive control of
β
K. Najim; A. S. Poznyak
π
Article
π
1998
π
John Wiley and Sons
π
English
β 161 KB
π 2 views
Convergence of the optimal values of con
β
Jorge Alvarez-Mena; OnΓ©simo HernΓ‘ndez-Lerma
π
Article
π
2002
π
Springer
π
English
β 267 KB
A note on the convergence rate of the va
β
Rolando Cavazos-Cadena
π
Article
π
1998
π
Elsevier Science
π
English
β 106 KB
The convergence of value iteration in av
β
Linn I. Sennott
π
Article
π
1996
π
Elsevier Science
π
English
β 415 KB
On the exact simulation of functionals o
β
Jean-Marc Vincent; Corine Marchand
π
Article
π
2004
π
Elsevier Science
π
English
β 410 KB
The effect of the Markov chain condition
β
A. Naess
π
Article
π
1984
π
Elsevier Science
π
English
β 883 KB
The purpose of this paper is to study the effect of correlation on extreme value estimates of a narrow-band, stationary Gaussian process. This is done by introducing a Markov chain condition on the sequence of peak values of the process. It is shown that this leads to extreme value estimates that ar