Turnpikes in finite Markov decision processes and random walk
Teoriâ veroâtnostej i ee primeneniâ, Tome 68 (2023) no. 1, pp. 147-176
Voir la notice de l'article provenant de la source Math-Net.Ru
In this paper we revise the theory of turnpikes in discounted Markov decision processes, prove the turnpike theorem for the undiscounted model, and apply the results to the specific random walk.
Keywords:
turnpike, Markov decision process, discounted reward, average reward, random walk, stochastic knapsack problem.
@article{TVP_2023_68_1_a8,
author = {A. B. Piunovskiy},
title = {Turnpikes in finite {Markov} decision processes and random walk},
journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
pages = {147--176},
publisher = {mathdoc},
volume = {68},
number = {1},
year = {2023},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/TVP_2023_68_1_a8/}
}
A. B. Piunovskiy. Turnpikes in finite Markov decision processes and random walk. Teoriâ veroâtnostej i ee primeneniâ, Tome 68 (2023) no. 1, pp. 147-176. http://geodesic.mathdoc.fr/item/TVP_2023_68_1_a8/