Knapsack Based Optimal Policies for Budget-Limited Multi-Armed Bandits

Long Tran-Thanh, Archie C. Chapman, Alex Rogers, Nicholas R. Jennings. Knapsack Based Optimal Policies for Budget-Limited Multi-Armed Bandits. In Jörg Hoffmann, Bart Selman, editors, Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada. pages 1134-1140, AAAI Press, 2012. [doi]

Abstract

Abstract is missing.