Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile, Yishay Mansour
We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir (2011). Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph. We also show that in the undirected case, the learner can achieve optimal regret without even accessing the observability graph before selecting an action. Both results are shown using variants of the Exp3 algorithm operating on the observability graph in a time-efficient manner.