A Reinforcement learning method for Optical Thin-Film Design
This work addresses the challenge of automated material search for optical thin-film design, which is incremental as it builds on existing machine learning methods in the field.
The authors tackled the problem of automated material search in optical thin-film inverse design by proposing a new end-to-end algorithm combining unsupervised learning, reinforcement learning, and a genetic algorithm, which was demonstrated to optimize the spectra of a multi-layer solar absorber device.
Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning(RL) and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.