Multilayer optical thin film design with deep Q learning

Anqing Jiang; Yoshie Osamu; Liangyao Chen

doi:10.1038/s41598-020-69754-w

Multilayer optical thin film design with deep Q learning

Anqing Jiang^*, Yoshie Osamu, Liangyao Chen

^*Corresponding author for this work

Graduate School of Information, Production and Systems

Research output: Contribution to journal › Article › peer-review

21 Citations (Scopus)

Abstract

Multilayer optical film plays a significant role in broad fields of optical application. Due to the nonlinear relationship between the dispersion characteristics of optical materials and the actual performance parameters of optical thin films, it is challenging to optimize optical thin film structure with the traditional models. In this paper, we present an implementation of Deep Q-learning, which suited for the most part for optical thin film. As a set of concrete demonstrations, we optimize solar absorber. The optimal program could optimal this solar absorber in 500 epoch (about 200 steps per-epoch) without any human intervention. Search results perform better than researchers’ manual searches.

Original language	English
Article number	12780
Journal	Scientific reports
Volume	10
Issue number	1
DOIs	https://doi.org/10.1038/s41598-020-69754-w
Publication status	Published - 2020 Dec 1

ASJC Scopus subject areas

General

Access to Document

10.1038/s41598-020-69754-w

Cite this

@article{d696dd9fdabc44bf94234ccbccd710c2,

title = "Multilayer optical thin film design with deep Q learning",

abstract = "Multilayer optical film plays a significant role in broad fields of optical application. Due to the nonlinear relationship between the dispersion characteristics of optical materials and the actual performance parameters of optical thin films, it is challenging to optimize optical thin film structure with the traditional models. In this paper, we present an implementation of Deep Q-learning, which suited for the most part for optical thin film. As a set of concrete demonstrations, we optimize solar absorber. The optimal program could optimal this solar absorber in 500 epoch (about 200 steps per-epoch) without any human intervention. Search results perform better than researchers{\textquoteright} manual searches.",

author = "Anqing Jiang and Yoshie Osamu and Liangyao Chen",

note = "Publisher Copyright: {\textcopyright} 2020, The Author(s).",

year = "2020",

month = dec,

day = "1",

doi = "10.1038/s41598-020-69754-w",

language = "English",

volume = "10",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Multilayer optical thin film design with deep Q learning

AU - Jiang, Anqing

AU - Osamu, Yoshie

AU - Chen, Liangyao

PY - 2020/12/1

Y1 - 2020/12/1

N2 - Multilayer optical film plays a significant role in broad fields of optical application. Due to the nonlinear relationship between the dispersion characteristics of optical materials and the actual performance parameters of optical thin films, it is challenging to optimize optical thin film structure with the traditional models. In this paper, we present an implementation of Deep Q-learning, which suited for the most part for optical thin film. As a set of concrete demonstrations, we optimize solar absorber. The optimal program could optimal this solar absorber in 500 epoch (about 200 steps per-epoch) without any human intervention. Search results perform better than researchers’ manual searches.

AB - Multilayer optical film plays a significant role in broad fields of optical application. Due to the nonlinear relationship between the dispersion characteristics of optical materials and the actual performance parameters of optical thin films, it is challenging to optimize optical thin film structure with the traditional models. In this paper, we present an implementation of Deep Q-learning, which suited for the most part for optical thin film. As a set of concrete demonstrations, we optimize solar absorber. The optimal program could optimal this solar absorber in 500 epoch (about 200 steps per-epoch) without any human intervention. Search results perform better than researchers’ manual searches.

UR - http://www.scopus.com/inward/record.url?scp=85088698417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088698417&partnerID=8YFLogxK

U2 - 10.1038/s41598-020-69754-w

DO - 10.1038/s41598-020-69754-w

M3 - Article

C2 - 32728183

AN - SCOPUS:85088698417

SN - 2045-2322

VL - 10

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 12780

ER -

Multilayer optical thin film design with deep Q learning

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this