Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.24177 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917361182834688 |
|---|---|
| author | Song, Ji Seok Kim, Se Kwon Kim, Kyoung-Min |
| author_facet | Song, Ji Seok Kim, Se Kwon Kim, Kyoung-Min |
| contents | Generating stable magnetic skyrmions is essential for the practical application of skyrmion-based spintronic devices in thermally agitating environments. Recent advancements have enabled the creation of skyrmions by controlling stripe domain instability through dynamic magnetic-field control. However, deterministic skyrmion creation and effectively managing the thermal stability of skyrmions remain challenges. Here, we present a deep reinforcement learning (DRL) approach to identify advanced dynamic magnetic-field-temperature paths that create skyrmions while controlling stripe domain instability and enhancing their 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, which tends to suppress internal excitation modes associated with skyrmion 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 DRL-powered search streamlines the identification of optimized protocols for skyrmion creation and control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24177 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimized control protocols for stable skyrmion creation using deep reinforcement learning Song, Ji Seok Kim, Se Kwon Kim, Kyoung-Min Mesoscale and Nanoscale Physics Disordered Systems and Neural Networks Statistical Mechanics Generating stable magnetic skyrmions is essential for the practical application of skyrmion-based spintronic devices in thermally agitating environments. Recent advancements have enabled the creation of skyrmions by controlling stripe domain instability through dynamic magnetic-field control. However, deterministic skyrmion creation and effectively managing the thermal stability of skyrmions remain challenges. Here, we present a deep reinforcement learning (DRL) approach to identify advanced dynamic magnetic-field-temperature paths that create skyrmions while controlling stripe domain instability and enhancing their 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, which tends to suppress internal excitation modes associated with skyrmion 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 DRL-powered search streamlines the identification of optimized protocols for skyrmion creation and control. |
| title | Optimized control protocols for stable skyrmion creation using deep reinforcement learning |
| topic | Mesoscale and Nanoscale Physics Disordered Systems and Neural Networks Statistical Mechanics |
| url | https://arxiv.org/abs/2603.24177 |