From Bandits to Experts: A Tale of Domination and Independence
Abstract
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.
Cite
Text
Alon et al. "From Bandits to Experts: A Tale of Domination and Independence." Neural Information Processing Systems, 2013.Markdown
[Alon et al. "From Bandits to Experts: A Tale of Domination and Independence." Neural Information Processing Systems, 2013.](https://mlanthology.org/neurips/2013/alon2013neurips-bandits/)BibTeX
@inproceedings{alon2013neurips-bandits,
title = {{From Bandits to Experts: A Tale of Domination and Independence}},
author = {Alon, Noga and Cesa-Bianchi, Nicolò and Gentile, Claudio and Mansour, Yishay},
booktitle = {Neural Information Processing Systems},
year = {2013},
pages = {1610-1618},
url = {https://mlanthology.org/neurips/2013/alon2013neurips-bandits/}
}