EUVIMEDEUVIMED entdecken
Crossref

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

Sébastien Bubeck, Nicolò Cesa-Bianchi

Foundations and Trends® in Machine Learning · 12.12.2012 · 5 (1) · 1-122

DOI: 10.1561/2200000024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Foundations and Trends® in Machine Learning, online erschienen am 12.12.2012. Verfasst von Sébastien Bubeck und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1123-mal zitiert (Crossref) und nennt 175 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration–exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. Although the study of bandit problems dates back to the 1930s, exploration–exploitation trade-offs arise in several modern applications, such as ad placement, website optimization, and packet routing. Mathematically, a multi-armed bandit is defined by the payoffs process associated with each option. In this monograph, we focus on two extreme cases in which the analysis of regret is particularly simple and elegant: i.i.d. payoffs and adversarial payoffs. Besides the basic setting of finitely many actions, we also analyze some of the most important variants and extensions, such as the contextual bandit model.

Zitieren

APA

Bubeck, S., & Cesa-Bianchi, N. (2012). Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems. Foundations and Trends® in Machine Learning, 5(1), 1-122. https://doi.org/10.1561/2200000024

Vancouver

Bubeck S, Cesa-Bianchi N. Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems. Foundations and Trends® in Machine Learning. 2012;5(1):1-122. doi:10.1561/2200000024

BibTeX
@article{Bubeck2012,
  author = {Bubeck, Sébastien and Cesa-Bianchi, Nicolò},
  title = {Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems},
  journal = {Foundations and Trends® in Machine Learning},
  year = {2012},
  volume = {5},
  number = {1},
  pages = {1--122},
  doi = {10.1561/2200000024}
}
Kostenlos starten →