Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning

TL;DR

This paper introduces PHORCED, a reinforcement learning-inspired probabilistic neural network method for inverse photonic device design, outperforming traditional gradient-based methods and enabling efficient transfer learning with fewer simulations.

Contribution

The paper presents PHORCED, a novel inverse design technique using policy gradient methods, demonstrating improved performance and transfer learning capabilities in photonic device design.

Findings

PHORCED outperforms local gradient-based inverse design methods.

Transfer learning with PHORCED reduces the number of required simulations.

PHORCED achieves faster convergence compared to state-of-the-art generative methods.

Abstract

We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design). This technique uses a probabilistic generative neural network interfaced with an electromagnetic solver to assist in the design of photonic devices, such as grating couplers. We show that PHORCED obtains better performing grating coupler designs than local gradient-based inverse design via the adjoint method, while potentially providing faster convergence over competing state-of-the-art generative methods. As a further example of the benefits of this method, we implement transfer learning with PHORCED, demonstrating that a neural network trained to optimize 8$^\circ$ grating couplers can then be re-trained on grating couplers with alternate scattering angles while requiring >10$\times$ fewer simulations than control cases.