Sample-efficient inverse design of freeform nanophotonic devices with physics-informed reinforcement learning
Abstract: 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 efficiency by an order of magnitude compared to conventional reinforcement learning and overcome the issue of local minima. To illustrate these advantages of PIRL over other conventional optimization algorithms, we design a family of one-dimensional metasurface beam deflectors using PIRL, exceeding most reported records. We also explore the transfer learning capability of PIRL that further improves sample efficiency and demonstrate how the minimum feature size of the design can be enforced in PIRL through reward engineering. With its high sample efficiency, robustness, and ability to seamlessly incorporate practical device design constraints, our method offers a promising approach to highly combinatorial freeform device optimization in various physical domains.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Sample-efficient inverse design of freeform nanophotonic devices with physics-informed reinforcement learning ; volume:13 ; number:8 ; year:2024 ; pages:1483-1492 ; extent:10
Nanophotonics ; 13, Heft 8 (2024), 1483-1492 (gesamt 10)
- Urheber
-
Park, Chaejin
Kim, Sanmun
Jung, Anthony W.
Park, Juho
Seo, Dongjin
Kim, Yongha
Park, Chanhyung
Park, Chan Y.
Jang, Min Seok
- DOI
-
10.1515/nanoph-2023-0852
- URN
-
urn:nbn:de:101:1-2024040616000747418693
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
14.08.2025, 10:55 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Park, Chaejin
- Kim, Sanmun
- Jung, Anthony W.
- Park, Juho
- Seo, Dongjin
- Kim, Yongha
- Park, Chanhyung
- Park, Chan Y.
- Jang, Min Seok
Ähnliche Objekte (12)
Inverse design of free-form nanophotonic devices
Physics-Informed Particle-Based Reinforcement Learning for Autonomy in Signalized Intersections
Free-form optimization of nanophotonic devices: from classical methods to deep learning
Stiff-PDEs and Physics-Informed Neural Networks
Physics-informed shape optimization using coordinate projection
Physics‐Informed Inverse Design of Programmable Metasurfaces
Physics-informed regression of implicitly-constrained robot dynamics
Predicting glass structure by physics-informed machine learning
Physics-Informed Masked Autoencoder for active sparse imaging
Physics-Informed Deep Learning for Advanced Medical Ultrasound
A physically-informed machine learning model for freeform bending
Learning free-surface flow with physics-informed neural networks
Inverse design of free-form nanophotonic devices
Physics-Informed Particle-Based Reinforcement Learning for Autonomy in Signalized Intersections
Free-form optimization of nanophotonic devices: from classical methods to deep learning
Stiff-PDEs and Physics-Informed Neural Networks
Physics-informed shape optimization using coordinate projection
Physics‐Informed Inverse Design of Programmable Metasurfaces
Physics-informed regression of implicitly-constrained robot dynamics
Predicting glass structure by physics-informed machine learning
Physics-Informed Masked Autoencoder for active sparse imaging
Physics-Informed Deep Learning for Advanced Medical Ultrasound
A physically-informed machine learning model for freeform bending
Learning free-surface flow with physics-informed neural networks
Inverse design of free-form nanophotonic devices
Physics-Informed Particle-Based Reinforcement Learning for Autonomy in Signalized Intersections
Free-form optimization of nanophotonic devices: from classical methods to deep learning
Stiff-PDEs and Physics-Informed Neural Networks
Physics-informed shape optimization using coordinate projection
Physics‐Informed Inverse Design of Programmable Metasurfaces
Physics-informed regression of implicitly-constrained robot dynamics
Predicting glass structure by physics-informed machine learning
Physics-Informed Masked Autoencoder for active sparse imaging
Physics-Informed Deep Learning for Advanced Medical Ultrasound
A physically-informed machine learning model for freeform bending