On asymptotic estimates in a~dynamic decision-making
Teoriâ veroâtnostej i ee primeneniâ, Tome 14 (1969) no. 2, pp. 250-268
Voir la notice de l'article provenant de la source Math-Net.Ru
An optimal control problem for a Markov process (with finite number of states in the stochastic version and with infinite number of states in the deterministic version) is considered. A generalization of the results due to Bellman and Romanovsky concerning the asymptotic representation of the maximal return as a function of the total number of steps is obtained.
@article{TVP_1969_14_2_a5,
author = {B. G. Pittel'},
title = {On asymptotic estimates in a~dynamic decision-making},
journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
pages = {250--268},
publisher = {mathdoc},
volume = {14},
number = {2},
year = {1969},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/TVP_1969_14_2_a5/}
}
B. G. Pittel'. On asymptotic estimates in a~dynamic decision-making. Teoriâ veroâtnostej i ee primeneniâ, Tome 14 (1969) no. 2, pp. 250-268. http://geodesic.mathdoc.fr/item/TVP_1969_14_2_a5/