Sub-sampling for Efficient Non-Parametric Bandit Exploration
Abstract
In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (namely Bernoulli, Gaussian and Poisson distributions). Unlike Thompson Sampling which requires to specify a different prior to be optimal in each case, our proposal RB-SDA does not need any distribution-dependent tuning. RB-SDA belongs to the family of Sub-sampling Duelling Algorithms (SDA) which combines the sub-sampling idea first used by the BESA [1] and SSMC [2] algorithms with different sub-sampling schemes. In particular, RB-SDA uses Random Block sampling. We perform an experimental study assessing the flexibility and robustness of this promising novel approach for exploration in bandit models.
Keywords
Cite
@article{arxiv.2010.14323,
title = {Sub-sampling for Efficient Non-Parametric Bandit Exploration},
author = {Dorian Baudry and Emilie Kaufmann and Odalric-Ambrym Maillard},
journal= {arXiv preprint arXiv:2010.14323},
year = {2020}
}
Comments
NeurIPS 2020, Dec 2020, Vancouver, Canada