A Tutorial on Thompson Sampling
Foundations and Trends® in Machine Learning · 12.07.2018 · 11 (1) · 1-96
DOI: 10.1561/2200000070 ↗Kurz gefasst
Fachartikel in der Zeitschrift Foundations and Trends® in Machine Learning, online erschienen am 12.07.2018. Verfasst von Daniel J. Russo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 421-mal zitiert (Crossref) und nennt 84 Literaturangaben.
Abstract (Originalsprache)
Thompson sampling is an algorithm for online decision problems where actions are taken sequentially in a manner that must balance between exploiting what is known to maximize immediate performance and investing to accumulate new information that may improve future performance. The algorithm addresses a broad range of problems in a computationally efficient manner and is therefore enjoying wide use. This tutorial covers the algorithm and its application, illustrating concepts through a range of examples, including Bernoulli bandit problems, shortest path problems, product recommendation, assortment, active learning with neural networks, and reinforcement learning in Markov decision processes. Most of these problems involve complex information structures, where information revealed by taking an action informs beliefs about other actions. We will also discuss when and why Thompson sampling is or is not effective and relations to alternative algorithms.
Zitieren
APA
Russo, D. J., Roy, B. V., Kazerouni, A., Osband, I., & Wen, Z. (2018). A Tutorial on Thompson Sampling. Foundations and Trends® in Machine Learning, 11(1), 1-96. https://doi.org/10.1561/2200000070
Vancouver
Russo DJ, Roy BV, Kazerouni A, Osband I, Wen Z. A Tutorial on Thompson Sampling. Foundations and Trends® in Machine Learning. 2018;11(1):1-96. doi:10.1561/2200000070
BibTeX
@article{Russo2018,
author = {Russo, Daniel J. and Roy, Benjamin Van and Kazerouni, Abbas and Osband, Ian and Wen, Zheng},
title = {A Tutorial on Thompson Sampling},
journal = {Foundations and Trends® in Machine Learning},
year = {2018},
volume = {11},
number = {1},
pages = {1--96},
doi = {10.1561/2200000070}
}
EUVIMED