Exploration–exploitation tradeoff using variance estimates in multi-armed bandits
Under an Elsevier user license
open archive
Keywords
Exploration–exploitation tradeoff
Multi-armed bandits
Bernstein’s inequality
High-probability bound
Risk analysis
Cited by (0)
- 1
Csaba Szepesvári is on leave from MTA SZTAKI, Budapest, Hungary.
Copyright © 2009 Elsevier B.V. All rights reserved.