The Asymptotic Behavior of Undiscounted Value Iteration in Markov Decision Problems

Autor:	Schweitzer, P. J., Federgruen, A.
Zdroj:	Mathematics of Operations Research, 1977 Nov 01. 2(4), 360-381.
Databáze:	JSTOR Journals
Externí odkaz:	https://www.jstor.org/stable/3689559 Zobrazit plný text záznamu