From bandits to experts: A tale of domination and independence

Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile, Yishay Mansour

Research output: Contribution to journalConference articlepeer-review


We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir [14]. 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 (which must be accessible before selecting an action). In the undirected case, we show that 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.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
StatePublished - 2013
Event27th Annual Conference on Neural Information Processing Systems, NIPS 2013 - Lake Tahoe, NV, United States
Duration: 5 Dec 201310 Dec 2013


Dive into the research topics of 'From bandits to experts: A tale of domination and independence'. Together they form a unique fingerprint.

Cite this