Generative Neural Network Based Non-Convex Optimization Using Policy Gradients with an Application to Electromagnetic Design

Sean Hooten, Sri Krishna` Vadlamani, Raymond G. Beausoleil, Thomas Van Vaerenbergh

Keywords: reinforcement learning, machine learning, generative neural network, policy gradient, optimization, inverse design, adjoint method, physics, electromagnetics, photonics, grating coupler

TL;DR: A generative neural network based non-convex optimization algorithm using a one-step implementation of the policy gradient method is introduced and applied to grating coupler design, resulting in state-of-the-art performance.

Abstract: A generative neural network based non-convex optimization algorithm using a one-step implementation of the policy gradient method is introduced and applied to electromagnetic design. We demonstrate state-of-the-art performance of electromagnetic devices called grating couplers, with key advantages over local gradient-based optimization via the adjoint method.

Track: Original Research Track