Parallel photonic accelerator for decision making using optical spatiotemporal chaos

Photonic accelerators have attracted increasing attention for use in artificial intelligence applications. The multi-armed bandit problem is a fundamental problem of decision making using reinforcement learning. However, to the best of our knowledge, the scalability of photonic decision making has n...

Full description

Saved in:
Bibliographic Details
Published in:Optica 2023-03, Vol.10 (3), p.339
Main Authors: Morijiri, Kensei, Takehana, Kento, Mihana, Takatomo, Kanno, Kazutaka, Naruse, Makoto, Uchida, Atsushi
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Photonic accelerators have attracted increasing attention for use in artificial intelligence applications. The multi-armed bandit problem is a fundamental problem of decision making using reinforcement learning. However, to the best of our knowledge, the scalability of photonic decision making has not yet been demonstrated in experiments because of the technical difficulties in the physical realization. We propose a parallel photonic decision-making system to solve large-scale multi-armed bandit problems using optical spatiotemporal chaos. We solved a 512-armed bandit problem online, which is larger than those in previous experiments by two orders of magnitude. The scaling property for correct decision making is examined as a function of the number of slot machines, evaluated as an exponent of 0.86. This exponent is smaller than that in previous studies, indicating the superiority of the proposed parallel principle. This experimental demonstration facilitates photonic decision making to solve large-scale multi-armed bandit problems for future photonic accelerators.
ISSN:2334-2536
2334-2536
DOI:10.1364/OPTICA.477433