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

Abstract

In the field of optics, precise control of light with arbitrary spatial resolution has long been a sought-after goal. Freeform nanophotonic devices are critical building blocks for achieving this goal, as they provide access to a design potential that could hardly be achieved by conventional fixed-shape devices. However, finding an optimal device structure in the vast combinatorial design space that scales exponentially with the number of freeform design parameters has been an enormous challenge. In this study, we propose physics-informed reinforcement learning (PIRL) as an optimization method for freeform nanophotonic devices, which combines the adjoint-based method with reinforcement learning to enhance the sample efficiency of the optimization algorithm 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, obtaining more performant devices. 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.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Optical Hyperlens: Far-field imaging beyond the diffraction limit
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• High-NA Achromatic Metalenses by Inverse Design
• Neural Combinatorial Optimization with Reinforcement Learning
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Simulator-based training of generative models for the inverse design of metasurfaces
• Planck intermediate results. XXIV. Constraints on variation of fundamental constants
• Physics-Informed Model-Based Reinforcement Learning
• PhysQ: A Physics Informed Reinforcement Learning Framework for Building Control

Cited by in corpus (2)

• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Data-Efficient Electromagnetic Surrogate Solver Through Dissipative Relaxation Transfer Learning