Reinforcement learning from demonstration for robust control of superconducting qubits: Decoherence suppression via environmental engineering

Chafaa  Hamrouni; Leila  Abdelgader

doi:10.59400/adecp3910

Reinforcement learning from demonstration for robust control of superconducting qubits: Decoherence suppression via environmental engineering

Chafaa Hamrouni
Advanced Department of Computer Sciences, Taif University–Khurma University College, Al-Khurma 2935, Saudi Arabia
Leila Abdelgader
Advanced Department of Computer Sciences, Taif University–Khurma University College, Al-Khurma 2935, Saudi Arabia

Article ID: 3910

Keywords: quantum control; transient emission spectra; squeezed reservoirs; feedback control; field purity engineering; open quantum systems; pulse shaping; qubit dynamics

Abstract

This work develops a control-oriented theoretical framework for the manipulation of transient emission spectra and field-state purity in a qubit interacting with a broadband squeezed reservoir. We model the joint qubit-field dynamics using a time-resolved open quantum system formalism. This establishes a direct, quantitative connection between transient spectral characteristics, quantum purity evolution, and controllable system parameters. The analysis reveals that nonclassical reservoir properties, particularly squeezing-induced correlations, strongly influence both spectral deformation and coherence redistribution during the early-time dynamics. Building on this foundation, the work explores practical control strategies aimed at engineering the system’s dynamical response. Pulse shaping and time-dependent modulation of qubit-reservoir coupling offer effective control tools. These regulate spectral broadening, suppress unwanted decoherence, and accelerate convergence toward stabilized operating regimes. In addition, feedback-assisted qubit probing protocols are investigated as a means of monitoring and controlling field purity while minimizing measurement back-action on the squeezed mode. Our results show that well-designed control loops can balance information extraction and disturbance. This enables efficient regulation of nonclassical field properties. The proposed approach highlights transient spectral measurements as a powerful diagnostic and control resource, linking observable emission features to underlying quantum correlations and purity dynamics. From an engineering perspective, the framework offers practical guidelines. These guide the design of feedback-stabilized quantum emitters and reservoir-engineered coherence control. These findings are directly relevant to emerging quantum technologies, including cavity and circuit quantum electrodynamics, quantum sensing, and quantum communication systems operating in nonclassical environments.

Published

2026-03-17

How to Cite

Hamrouni, C., & Abdelgader, L. (2026). Reinforcement learning from demonstration for robust control of superconducting qubits: Decoherence suppression via environmental engineering. Advances in Differential Equations and Control Processes, 33(1). https://doi.org/10.59400/adecp3910

Download Citation

Issue

Vol. 33 No. 1 (2026)

Section

Article

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Levenson-Falk EM, Shanto SA. A review of design concerns in superconducting quantum circuits. Materials for Quantum Technology. 2025; 5(2): 022003. doi: 10.1088/2633-4356/ade10d

[2]Rubin AH, Marinelli B, Norman VA, et al. Digital quantum simulation of cavity quantum electrodynamics: insights from superconducting and trapped ion quantum testbeds. Quantum Science and Technology. 2025; 10(4): 045057. doi: 10.1088/2058-9565/ae0af0

[3]Al-Sawai WM. Quantum dynamics of a cantilever under combined additive and parametric noise: Implications for squeezing and sensitivity control. Journal of Applied Physics. 2025; 138(16): 164401. doi: 10.1063/5.0291465

[4]Delfanazari K. Chip-scale electrically driven superconducting coherent photon sources for quantum information processing. Nature Photonics. 2025; 19(11): 1163–1177. doi: 10.1038/s41566-025-01735-9

[5]Wu Y, Xu M, Tang HX. Junction-free microwave two-mode radiation from a kinetic inductance nanowire. Physical Review Applied. 2024; 21(1): 014029. doi: 10.1103/PhysRevApplied.21.014029

[6]Khalifa M, Feldmann P, Salfi J. Kinetic inductance parametric converter. Physical Review Applied. 2024; 22(2): 024025. doi: 10.1103/PhysRevApplied.22.024025

[7]Jacobs K, Krastanov S, Heuck M, et al. Quantum theory of single-photon nonlinearities generated by ensembles of emitters. arXiv preprint. 2023. doi: 10.48550/arXiv.2307.01375

[8]Harraf H, Amazioug M, Laamara RA. Coherent feedback-enhanced asymmetry of thermal process in open quantum systems: Cavity optomechanics. arXiv preprint. 2025. doi: 10.48550/ARXIV.2512.13288

[9]Dagnaw Mekonnen H, Yeshiwas Y. Enhanced entanglement and synchronization in a coupled optomechanical system using a coherent feedback loop. Optics Continuum. 2026; 5(1): 196. doi: 10.1364/OPTCON.574353

[10]Mekonnen HD, Tesfahannes TG, Darge TY, et al. Boosting macroscopic entanglement in charged cavity optomechanical system through coherent feedback loop. Journal of Optics. 2025; 54(4): 2096–2104. doi: 10.1007/s12596-024-01926-7

[11]Yuan M, Seif A, Lingenfelter A, et al. Universal control in bosonic systems with weak Kerr nonlinearities. Physical Review A. 2025; 111(3): 032606. doi: 10.1103/PhysRevA.111.032606

[12]Liu ZX, Zuo XJ, Peng JX, et al. Quantum sensing with cavity optomechanics. Applied Physics Reviews. 2026; 13(1): 011307. doi: 10.1063/5.0237048

[13]Liu R, An JH. Quantum squeezed-reservoir engineering in Laguerre-Gaussian cavity optomechanics. Physical Review A. 2025; 111(4): 043718. doi: 10.1103/PhysRevA.111.043718

[14]Molinares H, Eremeev V. Drive-Loss Engineering and Quantum Discord Probing of Synchronized Optomechanical Squeezing. Mathematics. 2025; 13(13): 2171. doi: 10.3390/math13132171

[15]Tang Z, Li W, Sun H, et al. Cavity-optomechanical probe of gravity between massive mechanical oscillators. Physical Review A. 2025; 112(5): 053520. doi: 10.1103/m2zy-3ywx

[16]Luo Y, Diamandi HH, Li H, et al. Lifetime-limited Gigahertz-frequency Mechanical Oscillators with Millisecond Coherence Times. arXiv preprint. 2025. doi: 10.48550/ARXIV.2504.07523

[17]Ding Y, Chen X, Magdalena-Benedito R, et al. Closed-loop control of a noisy qubit with reinforcement learning. Machine Learning: Science and Technology. 2023; 4(2): 025020. doi: 10.1088/2632-2153/acd048

[18]Qiu W, Chen P, Liu S, et al. Interfacial phonon engineering in 2D heterostructures for cavity-less optomechanical systems. Journal of Applied Physics. 2025; 138(7): 073106. doi: 10.1063/5.0285259

[19]Satish MSS, Raj A, Dharmadhikari AK, et al. Thermally-tailored optical fiber lens: fundamentals, fabrication and advances. Journal of Optics. 2026; 28(1): 013001. doi: 10.1088/2040-8986/ae30f0

[20]Li S, Fan Y, Li X, et al. Robust quantum control using reinforcement learning from demonstration. npj Quantum Information. 2025; 11(1): 124. doi: 10.1038/s41534-025-01065-2

[21]Chatterjee A, Schwinger J, Gao YY. Enhanced Qubit Readout via Reinforcement Learning. Physical Review Applied. 2025; 23(5): 054057. doi: 10.1103/PhysRevApplied.23.054057

[22]Reuer K, Landgraf J, Fösel T, et al. Realizing a deep reinforcement learning agent for real-time quantum feedback. Nature Communications. 2023; 14(1): 7138. doi: 10.1038/s41467-023-42901-3

[23]Niu MY, Boixo S, Smelyanskiy VN, et al. Universal quantum control through deep reinforcement learning. npj Quantum Information. 2019; 5(1): 33. doi: 10.1038/s41534-019-0141-3

[24]Khalid I, Weidner CA, Jonckheere EA, et al. Sample-efficient model-based reinforcement learning for quantum control. Physical Review Research. 2023; 5(4): 043002. doi: 10.1103/PhysRevResearch.5.043002

[25]Fösel T, Tighineanu P, Weiss T, et al. Reinforcement Learning with Neural Networks for Quantum Feedback. Physical Review X. 2018; 8(3): 031084. doi: 10.1103/PhysRevX.8.031084

Early fault signals of the rolling bearing in the rotor are weak and present the characteristics of non-periodic and non-stationary; it is more difficult to carry out fault diagnosis on it. In this regard, this paper proposes a weak rolling bearing fault diagnosis algorithm based on whale optimization algorithm, simplistic geometry mode decomposition, and maximum correlated kurtosis deconvolution (WOA-SGMD-MCKD). Firstly, the vibration signal of the rotor platform is obtained, and the Symmetric Geometric Mode Decomposition (SGMD) is used to reconstruct the vibration signal. To obtain the best decomposition effect of the SGMD and overcome modal aliasing, the Whale Optimization Algorithm (WOA) is used to optimize the embedding dimension. Secondly, for the reconstructed vibration signal, the Maximum Correlated Kurtosis Deconvolution (MCKD) is used to extract its impulse component, and the WOA is used to optimize the filter length and deconvolution period of the MCKD so that the frequency envelope spectrum of the vibration signal can be obtained, which can provide the basis for the fault diagnosis of rolling bearings. Finally, the effectiveness and feasibility of the algorithm proposed are verified by a non-periodic and non-stationary simulation platform and rotor maneuvering platform in this paper.

Numerical solution of a 3D mathematical model for the progression of tumor angiogenic factor in a tissue

In this work, the movement of tumor angiogenic factor in a three-dimensional tissue is obtained by the Method of Lines. This method transforms a partial differential equation into a system of ordinary differential equations together with the initial and boundary conditions. The more the number of lines is increased, the more the accuracy of the method increases. This method results in very accurate numerical solutions for linear and non-linear problems in contrast with other existing methods. We present Matlab-generated figures, which are the movement of tumor angiogenic factor in porous medium and explain the biological importance of this progression. The computer codes are also provided.

Mathematical modelling and controllability analysis of fractional order coal mill pulverizer model

This paper investigates the controllability of nonlinear dynamical systems and their applications, with a focus on fractional-order systems and coal mill models. A novel theorem is proposed, providing sufficient conditions for controllability, including constraints on the steering operator and nonlinear perturbation bounds. The theorem establishes the existence of a contraction mapping for the nonlinear operator, enabling effective control strategies for fractional systems. The methodology is demonstrated through rigorous proof and supported by an iterative algorithm for controller design. Additionally, the controllability of a coal mill system represented as a nonlinear differential system, is analyzed. The findings present new insights into the interplay of fractional dynamics and nonlinear systems, offering practical solutions for real-world control problems.