Multi-armed Bandits with Cost Subsidy

no code implementations • 3 Nov 2020 • Deeksha Sinha, Karthik Abinav Sankararama, Abbas Kazerouni, Vashist Avadhanula

We then establish a fundamental lower bound on the performance of any online learning algorithm for this problem, highlighting the hardness of our problem in comparison to the classical MAB problem.

Multi-Armed Bandits Thompson Sampling