Biomimetic Ultra-Broadband Perfect Absorbers Optimised with Reinforcement Learning

Abstract

By learning the optimal policy with a double deep Q-learning network, we design ultra-broadband, biomimetic, perfect absorbers with various materials, based the structure of a moths eye. All absorbers achieve over 90% average absorption from 400 to 1,600 nm. By training a DDQN with motheye structures made up of chromium, we transfer the learned knowledge to other, similar materials to quickly and efficiently find the optimal parameters from the around 1 billion possible options. The knowledge learned from previous optimisations helps the network to find the best solution for a new material in fewer steps, dramatically increasing the efficiency of finding designs with ultra-broadband absorption.

References in corpus (2)

• Cross-modality deep learning brings bright-field microscopy contrast to holography
• Tungsten based metasurface absorber for visible regime

Cited by in corpus (7)

• Deep learning in nano-photonics: inverse design and beyond
• Intelligent metaphotonics empowered by machine learning
• Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs
• A topological encoding method for data-driven photonics inverse design
• Over 30,000-fold field enhancement of terahertz nanoresonators enabled by rapid inverse design
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning