English

Fully adaptive algorithm for pure exploration in linear bandits

Machine Learning 2017-10-17 v1

Abstract

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely fix sequences of arm selections before observing rewards, our method adaptively changes the arm selection strategy based on past observations at each round. We show our sample complexity matches the achievable lower bound up to a constant factor in an extreme case. Furthermore, we evaluate the performance of the methods by simulations based on both synthetic setting and real-world data, in which our method shows vast improvement over existing methods.

Keywords

Cite

@article{arxiv.1710.05552,
  title  = {Fully adaptive algorithm for pure exploration in linear bandits},
  author = {Liyuan Xu and Junya Honda and Masashi Sugiyama},
  journal= {arXiv preprint arXiv:1710.05552},
  year   = {2017}
}
R2 v1 2026-06-22T22:14:36.373Z