A Universal Approach to Nanophotonic Inverse Design through Reinforcement Learning

Marco Butz; Marco Butz; Alexander Leifhelm; Alexander Leifhelm; Marlon Becker; Benjamin Risse; Carsten Schuck; Carsten Schuck

doi:10.1364/CLEO_SI.2023.STh4G.3

CLEO 2023
Technical Digest Series (Optica Publishing Group, 2023),
paper STh4G.3
•https://doi.org/10.1364/CLEO_SI.2023.STh4G.3

A Universal Approach to Nanophotonic Inverse Design through Reinforcement Learning

Marco Butz, Alexander Leifhelm, Marlon Becker, Benjamin Risse, and Carsten Schuck

CLEO: Science and Innovations 2023

San Jose, CA United States
7–12 May 2023
ISBN: 978-1-957171-25-8

From the session
Computational Algorithms in Photonics (STh4G)

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
M. Butz, A. Leifhelm, M. Becker, B. Risse, and C. Schuck, "A Universal Approach to Nanophotonic Inverse Design through Reinforcement Learning," in CLEO 2023, Technical Digest Series (Optica Publishing Group, 2023), paper STh4G.3.

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Abstract

We present a novel method to perform universal black-box optimization of pixel-discrete nanophotonic devices based on reinforcement learning. We demonstrate the capabilities of our method for a silicon-on-insulator waveguide-mode converter with > 95% conversion efficiency.

PDF Article

More Like This

Metagrating Design based on Reinforcement Learning

Zi Wang, Wenqi Zhu, Junyeob Song, Lu Chen, Okan Koksal, and Amit Agrawal
FW4C.1 CLEO: Fundamental Science (CLEO:FS) 2023

OTF Gym: A Set of Reinforcement Learning Environment of Layered Optical Thin Film Inverse Design

Anqing Jiang, Liangyao Chen, and Osamu Yoshie
SM1Q.7 CLEO: Science and Innovations (CLEO:S&I) 2021

Inverse design and forward modelling in nanophotonics using deep-learning

Junsuk Rho
10a_N404_1 JSAP-OSA Joint Symposia (JSAP) 2021

Previous Article Next Article