文章基本信息

标题：Double-deep Q-learning to increase the efficiency of metasurface holograms
本地全文：下载
作者：Iman Sajedian ; Heon Lee ; Junsuk Rho 等
期刊名称：Scientific Reports
电子版ISSN：2045-2322
出版年度：2019
卷号：9
期号：1
页码：1-8
DOI：10.1038/s41598-019-47154-z
出版社：Springer Nature
摘要：We use a double deep Q-learning network (DDQN) to find the right material type and the optimal geometrical design for metasurface holograms to reach high efficiency. The DDQN acts like an intelligent sweep and could identify the optimal results in ~5.7 billion states after only 2169 steps. The optimal results were found between 23 different material types and various geometrical properties for a three-layer structure. The computed transmission efficiency was 32% for high-quality metasurface holograms; this is two times bigger than the previously reported results under the same conditions. The found structure is transmission-type and polarization-independent and works in the visible region.