On the Convergence of Policy Iteration in Stationary Dynamic Programming

Autor:	Puterman, Martin L., Brumelle, Shelby L.
Zdroj:	Mathematics of Operations Research, 1979 Feb 01. 4(1), 60-69.
Databáze:	JSTOR Journals
Externí odkaz:	https://www.jstor.org/stable/3689239 Zobrazit plný text záznamu