Decentralized multiagent reinforcement learning algorithm using a cluster-synchronized laser network
Physical Review E · 11.12.2024 · 110 (6)
DOI: 10.1103/physreve.110.064212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review E, online erschienen am 11.12.2024. Verfasst von Shun Kotoku und 3 weiteren Autor:innen. Beteiligte Einrichtung: The University of Tokyo, Department of Information Physics and Computing, Graduate School of Information Science and Technology, 7-3-1 Hongo, Bunkyo-…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Multiagent reinforcement learning (MARL) studies crucial principles that are applicable to a variety of fields, including wireless networking and autonomous driving. We propose a photonic-based decision-making algorithm to address one of the most fundamental problems in MARL, called the competitive multiarmed bandit (CMAB) problem. Our numerical simulations demonstrate that chaotic oscillations and cluster synchronization of optically coupled lasers, along with our proposed decentralized coupling adjustment, efficiently balance exploration and exploitation while facilitating cooperative decision making without explicitly sharing information among agents. Our study demonstrates how decentralized reinforcement learning can be achieved by exploiting complex physical processes controlled by simple algorithms.
Autor:innen und Institutionen
- The University of Tokyo, Department of Information Physics and Computing, Graduate School of Information Science and Technology, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Kotoku, S., Mihana, T., Röhm, A., & Horisaki, R. (2024). Decentralized multiagent reinforcement learning algorithm using a cluster-synchronized laser network. Physical Review E, 110(6). https://doi.org/10.1103/physreve.110.064212
Vancouver
Kotoku S, Mihana T, Röhm A, Horisaki R. Decentralized multiagent reinforcement learning algorithm using a cluster-synchronized laser network. Physical Review E. 2024;110(6). doi:10.1103/physreve.110.064212
BibTeX
@article{Kotoku2024,
author = {Kotoku, Shun and Mihana, Takatomo and Röhm, André and Horisaki, Ryoichi},
title = {Decentralized multiagent reinforcement learning algorithm using a cluster-synchronized laser network},
journal = {Physical Review E},
year = {2024},
volume = {110},
number = {6},
doi = {10.1103/physreve.110.064212}
}
EUVIMED