Multi-armed bandits and applications to large datasets

This thesis considers the multi-armed bandit (MAB) problem, both the traditional bandit feedback and graphical bandits when there is side information. Motivated by the Boltzmann exploration algorithm often used in the more general context of reinforcement learning, we present Almost Boltzmann Exploration (ABE) which fixes the under-exploration issue while maintaining an expression similar to Boltzmann exploration. We then present some real world applications of the MAB framework, comparing the performance of ABE with other bandit algorithms on real world datasets.U of I OnlyAuthor requested U of Illinois access only (OA after 2yrs) in Vireo ETD syste