Multi-armed bandit (MAB) is a popular framework for decision-making in an uncertain environment. In its classical setup, the algorithm has access to a fixed and finite set of unknown, independent probability distributions or arms.
Ad placement in web-browsing and wireless mobiles is an increasingly important component of the advertisement market. The market size is over $ 100 billion and counting.
Papers by:
(1)"Best Arm Identification in Multi-Armed Bandits" by Audibert and Bubeck, 2010.
(2)"Tight (Lower) Bounds for the Fixed Budget Best Arm IdentificationBandit Problem" Carpentier and Locatelli 2016.