Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits

Shahrampour, Shahin, Tarokh, Vahid

arXiv.org Machine Learning 

We address the M-best-arm identification problem in multi-armed bandits. A player has a limited budget to explore K arms (M

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found