Sample-efficient inverse design of freeform nanophotonic devices with physics-informed reinforcement learning

Sample-efficient inverse design of freeform nanophotonic devices with physics-informed reinforcement learning

Finding an optimal device structure in the vast combinatorial design space of freeform nanophotonic design has been an enormous challenge. In this study, we propose physics-informed reinforcement learning (PIRL) that combines the adjoint-based method with reinforcement learning to improve the sample...

Full description

Bibliographic Details
Main Authors: Park Chaejin, Kim Sanmun, Jung Anthony W., Park Juho, Seo Dongjin, Kim Yongha, Park Chanhyung, Park Chan Y., Jang Min Seok
Format: Article
Language:English
Published: De Gruyter 2024-02-01
Series:Nanophotonics
Subjects:
metasurface
adjoint-based method
reinforcement learning
physic-informed neural network
freeform design
inverse design
Online Access:https://doi.org/10.1515/nanoph-2023-0852

Internet

https://doi.org/10.1515/nanoph-2023-0852

Similar Items