A Note on Information-Directed Sampling and Thompson Sampling
Machine Learning
2015-03-25 v1 Artificial Intelligence
Abstract
This note introduce three Bayesian style Multi-armed bandit algorithms: Information-directed sampling, Thompson Sampling and Generalized Thompson Sampling. The goal is to give an intuitive explanation for these three algorithms and their regret bounds, and provide some derivations that are omitted in the original papers.
Cite
@article{arxiv.1503.06902,
title = {A Note on Information-Directed Sampling and Thompson Sampling},
author = {Li Zhou},
journal= {arXiv preprint arXiv:1503.06902},
year = {2015}
}