Automated Optical Multi-layer Design via Deep Reinforcement Learning

Abstract

Optical multi-layer thin films are widely used in optical and energy applications requiring photonic designs. Engineers often design such structures based on their physical intuition. However, solely relying on human experts can be time-consuming and may lead to sub-optimal designs, especially when the design space is large. In this work, we frame the multi-layer optical design task as a sequence generation problem. A deep sequence generation network is proposed for efficiently generating optical layer sequences. We train the deep sequence generation network with proximal policy optimization to generate multi-layer structures with desired properties. The proposed method is applied to two energy applications. Our algorithm successfully discovered high-performance designs, outperforming structures designed by human experts in task 1, and a state-of-the-art memetic algorithm in task 2.

15 pages, 10 figures, poster presentation at RL4RealLife 2020

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Training deep neural networks for the inverse design of nanophotonic structures
• Learning Combinatorial Optimization Algorithms over Graphs
• A Generative Model for Inverse Design of Metamaterials
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Device Placement Optimization with Reinforcement Learning
• Multilayer optical calculations
• Chip Placement with Deep Reinforcement Learning

Cited by in corpus (2)

• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• A Reinforcement learning method for Optical Thin-Film Design