Survival Multiarmed Bandits with Bootstrapping Methods

Determining optimal actions requires an appropriate balance of exploration and exploitation at each stage. In the traditional setting, actions which maximize the cumulative expected reward are deemed to be optimal. The MAB framework has seen many practical applications in a wide variety of fields like healthcare, finance, machine learning and telecommunication to name a few [Bouneffouf and Rish, 2019]. Recent literature has extended the bandits framework with alternative objectives such as Risk-Averse Multiarmed Bandits (RA-MAB) and Budgeted Multiarmed Bandits (B-MAB), which broaden the scope of applications of bandits models. The RA-MAB are concerned with the risk of rewards [Sani et al., 2012] and the B-MAB with a cost associated with each action that depletes a finite budget [Xia et al., 2017].