English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the field of optics, precise control of light with arbitrary spatialresolution has long been a sought-after goal. Freeform nanophotonic devices arecritical building blocks for achieving this goal, as they provide access to adesign potential that could hardly be achieved by conventional fixed-shapedevices. However, finding an optimal device structure in the vast combinatorialdesign space that scales exponentially with the number of freeform designparameters has been an enormous challenge. In this study, we proposephysics-informed reinforcement learning (PIRL) as an optimization method forfreeform nanophotonic devices, which combines the adjoint-based method withreinforcement learning to enhance the sample efficiency of the optimizationalgorithm and overcome the issue of local minima. To illustrate theseadvantages of PIRL over other conventional optimization algorithms, we design afamily of one-dimensional metasurface beam deflectors using PIRL, obtainingmore performant devices. We also explore the transfer learning capability ofPIRL that further improves sample efficiency and demonstrate how the minimumfeature size of the design can be enforced in PIRL through reward engineering.With its high sample efficiency, robustness, and ability to seamlesslyincorporate practical device design constraints, our method offers a promisingapproach to highly combinatorial freeform device optimization in variousphysical domains.

Physics-informed reinforcement learning for sample-efficient optimization of freeform nanophotonic devices