EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantum compiling with reinforcement learning on a superconducting processor

Z T Wang, Qiuhao Chen, Yuxuan Du, Z H Yang, Xiaoxia Cai, Kaixuan Huang, Jingning Zhang, Kai Xu, Jun Du, Yinan Li, Yuling Jiao, Xingyao Wu und 6 weitere

Machine Learning: Science and Technology · 01.08.2026 · 7 (4) · 045016

DOI: 10.1088/2632-2153/ae835e ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 09.07.2026. Verfasst von Z T Wang und 17 weiteren Autor:innen. Die Arbeit nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CPS-Yangtze Delta Region Industrial Innovation Center of Quantum and Information Technology-MindSpore Quantum Open Fund, National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effectively implementing quantum algorithms on noisy intermediate-scale quantum (NISQ) processors is a central task in modern quantum technology. NISQ processors feature tens to a few hundreds of noisy qubits with limited coherence times and gate operations with errors, so NISQ algorithms naturally require employing circuits of short lengths via quantum compilation. Here, we evaluate a reinforcement learning (RL)-based quantum compiler on a superconducting processor. Our experiments reveal that for two-qubit circuits, the RL-based compiler surpasses conventional methods, demonstrating its ability to discover hardware-amenable circuits with near-optimal lengths. However, for three-qubit circuits, the RL-based compiler does not achieve unity theoretical fidelity. To address this limitation, we integrate a variational strategy with the RL-based compiler, highlighting their complementary strengths. Systematic experiments show that this variational RL-based compiler consistently identifies near-optimal circuits, even under stringent hardware constraints, outperforming conventional techniques. Furthermore, we analyze the impact of decoherence and gate errors, providing critical insights into the practical performance of RL-based compilers on quantum hardware. These findings exemplify the codesign of the software with hardware for efficient quantum compilation, offering valuable insights for the advancement of RL-based compilers.

Förderung

  • CPS-Yangtze Delta Region Industrial Innovation Center of Quantum and Information Technology-MindSpore Quantum Open Fund
  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Beijing Nova Program
  • Fundamental Research Funds for the Central Universities
  • Fundamental Research for the Central Universities and Innovation Program for Quantum Science and Technology
  • National Nature Science Foundation of Hubei

Zitieren

APA

Wang, Z. T., Chen, Q., Du, Y., Yang, Z. H., Cai, X., Huang, K., Zhang, J., Xu, K., Du, J., Li, Y., Jiao, Y., Wu, X., Lu, X., Xu, H., Jin, Y., Wang, R., Yu, H., & Zhao, S. P. (2026). Quantum compiling with reinforcement learning on a superconducting processor. Machine Learning: Science and Technology, 7(4), 045016. https://doi.org/10.1088/2632-2153/ae835e

Vancouver

Wang ZT, Chen Q, Du Y, Yang ZH, Cai X, Huang K, et al. Quantum compiling with reinforcement learning on a superconducting processor. Machine Learning: Science and Technology. 2026;7(4):045016. doi:10.1088/2632-2153/ae835e

BibTeX
@article{Wang2026,
  author = {Wang, Z T and Chen, Qiuhao and Du, Yuxuan and Yang, Z H and Cai, Xiaoxia and Huang, Kaixuan and Zhang, Jingning and Xu, Kai and Du, Jun and Li, Yinan and Jiao, Yuling and Wu, Xingyao and Lu, Xiliang and Xu, Huikai and Jin, Yirong and Wang, Ruixia and Yu, Haifeng and Zhao, S P},
  title = {Quantum compiling with reinforcement learning on a superconducting processor},
  journal = {Machine Learning: Science and Technology},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {045016},
  doi = {10.1088/2632-2153/ae835e}
}
Kostenlos starten →