Hybrid Supervised and Reinforcement Learning for the Design and Optimization of Nanophotonic Structures

TL;DR

This paper introduces a hybrid supervised and reinforcement learning method for nanophotonic structure design, significantly reducing data requirements, enhancing generalization, and accelerating training compared to traditional approaches.

Contribution

It presents a novel hybrid learning framework that combines supervised and reinforcement learning to improve nanophotonic inverse design efficiency and effectiveness.

Findings

Reduces training data dependence

Improves model generalizability

Speeds up training by orders of magnitude

Abstract

From higher computational efficiency to enabling the discovery of novel and complex structures, deep learning has emerged as a powerful framework for the design and optimization of nanophotonic circuits and components. However, both data-driven and exploration-based machine learning strategies have limitations in their effectiveness for nanophotonic inverse design. Supervised machine learning approaches require large quantities of training data to produce high-performance models and have difficulty generalizing beyond training data given the complexity of the design space. Unsupervised and reinforcement learning-based approaches on the other hand can have very lengthy training or optimization times associated with them. Here we demonstrate a hybrid supervised learning and reinforcement learning approach to the inverse design of nanophotonic structures and show this approach can reduce training data dependence, improve the generalizability of model predictions, and shorten exploratory training times by orders of magnitude. The presented strategy thus addresses a number of contemporary deep learning-based challenges, while opening the door for new design methodologies that leverage multiple classes of machine learning algorithms to produce more effective and practical solutions for photonic design.