"Whittle index based Q-learning for restless bandits with average reward."

Konstantin E. Avrachenkov, Vivek S. Borkar (2022)

Details and statistics

DOI: 10.1016/J.AUTOMATICA.2022.110186

access: closed

type: Journal Article

metadata version: 2022-06-23

a service of  Schloss Dagstuhl - Leibniz Center for Informatics