1. Bandits with concave rewards and convex knapsacks;Agrawal,2014
2. A game theoretic formulation of the service provisioning problem in cloud systems;Ardagna,2011
3. Best arm identification in multi-armed bandits;Audibert,2010
4. Exploration-exploitation tradeoff using variance estimates in multi-armed bandits;Audibert;Theor. Comput. Sci.,2009
5. Using confidence bounds for exploitation-exploration trade-offs;Auer;J. Mach. Learn. Res.,2003