Optimized control protocols for stable skyrmion creation using deep reinforcement learning

Abstract

Generating stable magnetic skyrmions is essential for the practical application of skyrmion-based spintronic devices in thermally agitating environments. Here, we present a deep reinforcement learning (DRL) approach to identify advanced dynamic magnetic-field-temperature paths that create skyrmions with enhanced thermal stability. The trained DRL agent discovers an optimized field-temperature path that achieves a higher success rate for skyrmion formation in Fe3GeTe2 monolayers compared to previous fixed-temperature field sweeps. Additionally, the generated skyrmions exhibit longer lifetimes due to their isotropic shape and equilibrium size, both of which place them near a local energy minimum and thereby hinder annihilation. We demonstrate that these advancements stem from the targeted minimization of the dissipated work, which ensures that the driven skyrmion states remain close to their equilibrium distributions by upper-bounding the Kullback--Leibler divergence. Our findings suggest that a physics-informed DRL framework streamlines the identification of optimized protocols for skyrmion creation.