Reinforcement learning enabled the design of compact and efficient integrated photonic devices

TL;DR

This paper demonstrates how reinforcement learning can be used to design ultra-compact, efficient integrated photonic devices with low crosstalk, suitable for fabrication using existing semiconductor technologies.

Contribution

The study introduces a novel design methodology combining reinforcement learning with electromagnetic simulations to create smaller, high-performance photonic components.

Findings

Designed devices operate at 1550 nm wavelength.

Achieved device footprints of 3x3 micrometers squared.

Devices show improved performance over previous structures.

Abstract

In this paper, we introduce the design approach of integrated photonic devices by employing reinforcement learning known as attractor selection. Here, we combined three-dimensional finite-difference time-domain method with attractor selection algorithm, which is based on artificial neural networks, to achieve ultra-compact and highly efficient photonic devices with low crosstalk such as wavelength demultiplexers and a polarization splitter. The presented devices consist of silicon-on-insulator materials, which are compatible with complementary metal-oxide-semiconductor technology, and their structural dimensions enable the possible fabrication process in the future. The numerical results are presented for the near-infrared wavelengths at around 1550 nm, and the performance of designed photonic devices with footprint of 3x3 um2 are compared with the previously reported structures. Consequently, the reinforcement learning is successfully applied to design smaller and superior integrated photonic devices where the use of presented approach can be further expanded to different applications.