纳米光子学
反向
纳米材料
样品(材料)
强化学习
钢筋
纳米技术
材料科学
计算机科学
工程物理
物理
人工智能
数学
复合材料
几何学
热力学
作者
Chaejin Park,Sanmun Kim,Anthony W. Jung,Juho Park,Dongjin Seo,Yongha Kim,Chanhyung Park,Chan Y. Park,Min Seok Jang
出处
期刊:Nanophotonics
[De Gruyter]
日期:2024-02-27
卷期号:13 (8): 1483-1492
被引量:43
标识
DOI:10.1515/nanoph-2023-0852
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI