Gradient Ascent for Active Exploration in Bandit Problems
Machine Learning
2019-05-21 v1 Machine Learning
Abstract
We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting. This problem encompasses several well studied problems such that the Best Arm Identification or Thresholding Bandits. It consists of a new sampling rule based on an online lazy mirror ascent. We prove that this algorithm is asymptotically optimal and, most importantly, computationally efficient.
Keywords
Cite
@article{arxiv.1905.08165,
title = {Gradient Ascent for Active Exploration in Bandit Problems},
author = {Pierre Ménard},
journal= {arXiv preprint arXiv:1905.08165},
year = {2019}
}
Comments
21 pages, 1 figure