Index-Based Policies for Discounted Multi-Armed Bandits on Parallel Machines

Autor:	Glazebrook, K. D., Wilkinson, D. J.
Zdroj:	The Annals of Applied Probability, 2000 Aug 01. 10(3), 877-896.
Databáze:	JSTOR Journals
Externí odkaz:	https://www.jstor.org/stable/2667323 Zobrazit plný text záznamu