EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk

Tomoki Yamagami iD, Etsuo Segawa iD, Takatomo Mihana iD, André Röhm iD, Ryoichi Horisaki iD, Makoto Naruse iD

Entropy · 25.05.2023 · 25 (6) · 843

DOI: 10.3390/e25060843 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 25.05.2023. Verfasst von Tomoki Yamagami und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo,…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SPRING program, Japan Science and Technology Agency, Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantum walks (QWs) have a property that classical random walks (RWs) do not possess—the coexistence of linear spreading and localization—and this property is utilized to implement various kinds of applications. This paper proposes RW- and QW-based algorithms for multi-armed-bandit (MAB) problems. We show that, under some settings, the QW-based model realizes higher performance than the corresponding RW-based one by associating the two operations that make MAB problems difficult—exploration and exploitation—with these two behaviors of QWs.

Schlagwörter

Stichwörter der Autor:innen

bandit algorithmdecision-makingexploration–exploitation trade-offquantum walkrandom walk

Autor:innen und Institutionen

  • Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, Japan.
  • Graduate School of Environment and Information Sciences, Yokohama National University, 79-1 Tokiwadai, Hodogaya, Yokohama 240-8501, Kanagawa, Japan.

ORCID-Profile: Tomoki Yamagami, Etsuo Segawa, Takatomo Mihana, André Röhm, Ryoichi Horisaki, Makoto Naruse

Förderung

  • SPRING program
  • Japan Science and Technology Agency
  • Japan Society for the Promotion of Science

Zitieren

APA

Yamagami, T., Segawa, E., Mihana, T., Röhm, A., Horisaki, R., & Naruse, M. (2023). Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk. Entropy, 25(6), 843. https://doi.org/10.3390/e25060843

Vancouver

Yamagami T, Segawa E, Mihana T, Röhm A, Horisaki R, Naruse M. Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk. Entropy. 2023;25(6):843. doi:10.3390/e25060843

BibTeX
@article{Yamagami2023,
  author = {Yamagami, Tomoki and Segawa, Etsuo and Mihana, Takatomo and Röhm, André and Horisaki, Ryoichi and Naruse, Makoto},
  title = {Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk},
  journal = {Entropy},
  year = {2023},
  volume = {25},
  number = {6},
  pages = {843},
  doi = {10.3390/e25060843}
}
Kostenlos starten →