Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2603.18060

Reinforcement Learning for Fast and Robust Longitudinal Qubit Readout

Yiming Yu, Yuan Qiu, Xinyu Zhao, Ye-Hong Chen, Yan Xia

quant-phSubmitted Mar 18, 2026• Announced Mar 19, 2026• 0 citations
arXivHTMLPDF

Abstract

Longitudinal coupling offers a compelling pathway for quantum nondemolition (QND) readout, but pulse design is constrained by hardware limitations such as the coupling strength and the photon number required to stay within the linear regime. We develop a reinforcement learning framework to optimize the longitudinal coupling waveform under such constraints. Building upon the theoretical foundation of shortcuts to adiabaticity (STA), we parameterize an auxiliary trajectory with cubic B-splines and reconstruct the physical control. At a fixed short readout time, the optimized pulse converges to a constraint saturating flat-top protocol and yields a approximately $50\%$ improvement in $\mathrm{SNR}$ over an STA baseline, while exhibiting enhanced robustness to parameter drifts. Simulation results demonstrate the efficacy of reinforcement learning in optimizing longitudinal readout pulses. The optimized protocol attains substantial performance gains and yields smooth, hardware-compatible waveforms governed by an interpretable ``saturate-and-hold'' mechanism.

Comments
11 pages, 5 figures

Related papers

Enhanced qubit readout via reinforcement learning

Aniket Chatterjee, Jonathan Schwinger, Yvonne Y. Gao

Measurement is an essential component of robust and practical quantum computation. For superconducting qubits, the measurement process involves the effective manipulation of the joint qubit-resonator dynamics, and it should ideally provide the highest quality for qubit state discrimination with the shortest readout pulse and resonator reset time. Here, we harness model-free reinforcement learning (RL), together with a tailored training environment, to achieve this multifaceted optimization task. Using the IBM quantum device, we demonstrate that the pulse obtained by the RL agent not only successfully achieves state-of-the-art performance, with an assignment error of ( 4.6 ± 0.4 ) × 10 − 3 , but also executes the readout and the subsequent resonator reset almost three times faster than the system’s default process. Furthermore, the learned waveforms are robust against realistic parameter drifts and follow an intuitive form, making them readily implementable on existing hardware with little computational overhead. Our results provide an effective readout strategy to boost the performance of superconducting quantum processors and demonstrate the value of RL in providing optimal and practical solutions for complex quantum information processing tasks.

arXiv:2412.04053•Physical Review Applied•May 22, 2025•10 citations

Reinforcement Learning for Robust Calibration of Multi-Qudit Quantum Gates

Amine Jaouadi, Sahel Ashhab

Higher-dimensional quantum systems, such as qudits, offer architectural and algorithmic advantages over qubits, but their increased spectral crowding and limited controllability render high-fidelity quantum gates particularly challenging. We propose a hybrid optimization framework that integrates optimal control theory methods with contextual deep reinforcement learning to achieve robust controlled-phase gates on two qutrits. Optimal control is first used to design high-fidelity control pulses for a nominal system model. Reinforcement learning is then employed as a calibration stage that learns small residual corrections to these pulses in the presence of static model mismatch, thereby preserving good gate performance under realistic parameter uncertainties. By learning structured, low-dimensional residual corrections conditioned on device-specific parameter variations, reinforcement learning enhances the transfer robustness of nominally optimal but parameter-sensitive control solutions across ensembles of devices. Crucially, the reinforcement learning step in our framework does not compete with the optimal control step but provides the adaptability required for realistic hardware, systematically reducing the sensitivity to parameter fluctuations. Our results establish reinforcement learning as a practical and scalable ingredient for robust calibration of quantum gates in high-dimensional systems.

quant-pharXiv:2604.19990•Physical Review A•Apr 23, 2026•1 citation

Breaking adiabatic quantum control with deep learning

Yongcheng Ding, Yue Ban, José D. Martín‐Guerrero +3 more

In the noisy intermediate-scale quantum era, optimal digitized pulses are requisite for efficient quantum control. This goal is translated into dynamic programming, in which a deep reinforcement learning (DRL) agent is gifted. As a reference, shortcuts to adiabaticity (STA) provide analytical approaches to adiabatic speedup by pulse control. Here, we select the single-component control of qubits, resembling the ubiquitous two-level Landau-Zener problem for gate operation. We aim at obtaining fast and robust digital pulses by combining the STA and DRL algorithm. In particular, we find that DRL leads to robust digital quantum control with the operation time bounded by quantum speed limits dictated by STA. In addition, we demonstrate that robustness against systematic errors can be achieved by DRL without any input from STA. Our results introduce a general framework of digital quantum control, leading to a promising enhancement in quantum information processing.

arXiv:2009.04297•Physical Review A•Apr 9, 2021•49 citations

Achieving fast and robust perfect entangling gates via reinforcement learning

Leander Grech, Matthias G. Krauss, Mirko Consiglio +4 more

Noisy intermediate-scale quantum computers hold the promise of tackling complex and otherwise intractable computational challenges through the massive parallelism offered by qubits. Central to realizing the potential of quantum computing are perfect entangling (PE) two-qubit gates, which serve as a critical building block for universal quantum computation. In the context of quantum optimal control, shaping electromagnetic pulses to drive quantum gates is crucial for pushing gate performance toward theoretical limits. In this work, we leverage reinforcement learning (RL) techniques to discover near-optimal pulse shapes that yield PE gates. A collection of RL agents is trained within robust simulation environments, enabling the identification of effective control strategies even under noisy conditions. Selected agents are then validated on higher-fidelity simulations, illustrating how RL-based methods can reduce calibration overhead when compared to quantum optimal control techniques. Furthermore, the RL approach is hardware agnostic with the potential for broad applicability across various quantum computing platforms.

quant-pharXiv:2511.07076•Quantum Science and Technology•Nov 11, 2025•2 citations

Robust stimulated Raman shortcuts to adiabatic passage with deep learning

Chahrazed Messikh, Azeddine Messikh

Abstract One of the challenging tasks in quantum control is to manipulate quantum systems with high fidelity and as fast as possible. Simulated Raman shortcuts to adiabatic passage with invariant-based optimal control is an efficient technique accurately used to transfer population between two quantum states in three-level systems. This technique requires tuning parameters continuously which results in analog quantum control. However, a digital quantum controller design is of great importance in the era of digital quantum computing. Here, we use deep reinforcement learning to obtain digital Stokes and pump fields that can realize fast and accurate population transfer between states with the same parity in the three-level Λ configuration. We find that deep reinforcement learning follows exactly theshortcuts to adiabaticity (STA) based on dynamical invariant and leads to a robust population transfer against systematic errors and dephasing. This is a promising enhancement in digital quantum information processing.

Europhysics Letters (EPL)•Nov 1, 2022•4 citations

Robust quantum control using reinforcement learning from demonstration

Shengyong Li, Yidian Fan, Xiangyang Li +6 more

Quantum control requires high-precision and robust control pulses to ensure optimal system performance. However, control sequences generated with a system model may suffer from model bias, leading to low fidelity. While model-free reinforcement learning (RL) methods have been developed to avoid such biases, training an RL agent from scratch can be time-consuming, often taking hours to gather enough samples for convergence. This challenge has hindered the broad application of RL techniques to larger and more complex quantum control issues, limiting their adaptability. In this work, we use Reinforcement Learning from Demonstration (RLfD) to leverage the control sequences generated with system models and further optimize them with RL to avoid model bias. By avoiding learning from scratch and starting with reasonable control pulse shapes, this approach can increase sample efficiency by reducing the number of samples, which can significantly reduce the training time. Thus, this method can effectively handle pulse shapes that are discretized into more than 1000 pieces without compromising final fidelity. We have simulated the preparation of several high-fidelity non-classical states using the RLfD method. We also find that the training process is more stable when using RLfD. In addition, this method is suitable for fast gate calibration using reinforcement learning.

arXiv:2503.21085•npj Quantum Information•Jul 25, 2025•12 citations
Longitudinal coupling offers a compelling pathway for quantum nondemolition (QND) readout, but pulse design is constrained by hardware limitations such as the coupling strength and the photon number required to stay within the linear regime.
We develop a reinforcement learning framework to optimize the longitudinal coupling waveform under such constraints.
Building upon the theoretical foundation of shortcuts to adiabaticity (STA), we parameterize an auxiliary trajectory with cubic B-splines and reconstruct the physical control.
At a fixed short readout time, the optimized pulse converges to a constraint saturating flat-top protocol and yields a approximately 50%50\%50% improvement in SNR\mathrm{SNR}SNR over an STA baseline, while exhibiting enhanced robustness to parameter drifts.
Simulation results demonstrate the efficacy of reinforcement learning in optimizing longitudinal readout pulses.
The optimized protocol attains substantial performance gains and yields smooth, hardware-compatible waveforms governed by an interpretable ``saturate-and-hold'' mechanism.
Measurement is an essential component of robust and practical quantum computation. For superconducting qubits, the measurement process involves the effective manipulation of the joint qubit-resonator dynamics, and it should ideally provide the highest quality for qubit state discrimination with the shortest readout pulse and resonator reset time. Here, we harness model-free reinforcement learning (RL), together with a tailored training environment, to achieve this multifaceted optimization task. Using the IBM quantum device, we demonstrate that the pulse obtained by the RL agent not only successfully achieves state-of-the-art performance, with an assignment error of ( 4.6 ± 0.4 ) × 10 − 3 , but also executes the readout and the subsequent resonator reset almost three times faster than the system’s default process. Furthermore, the learned waveforms are robust against realistic parameter drifts and follow an intuitive form, making them readily implementable on existing hardware with little computational overhead. Our results provide an effective readout strategy to boost the performance of superconducting quantum processors and demonstrate the value of RL in providing optimal and practical solutions for complex quantum information processing tasks.
Higher-dimensional quantum systems, such as qudits, offer architectural and algorithmic advantages over qubits, but their increased spectral crowding and limited controllability render high-fidelity quantum gates particularly challenging. We propose a hybrid optimization framework that integrates optimal control theory methods with contextual deep reinforcement learning to achieve robust controlled-phase gates on two qutrits. Optimal control is first used to design high-fidelity control pulses for a nominal system model. Reinforcement learning is then employed as a calibration stage that learns small residual corrections to these pulses in the presence of static model mismatch, thereby preserving good gate performance under realistic parameter uncertainties. By learning structured, low-dimensional residual corrections conditioned on device-specific parameter variations, reinforcement learning enhances the transfer robustness of nominally optimal but parameter-sensitive control solutions across ensembles of devices. Crucially, the reinforcement learning step in our framework does not compete with the optimal control step but provides the adaptability required for realistic hardware, systematically reducing the sensitivity to parameter fluctuations. Our results establish reinforcement learning as a practical and scalable ingredient for robust calibration of quantum gates in high-dimensional systems.
In the noisy intermediate-scale quantum era, optimal digitized pulses are requisite for efficient quantum control. This goal is translated into dynamic programming, in which a deep reinforcement learning (DRL) agent is gifted. As a reference, shortcuts to adiabaticity (STA) provide analytical approaches to adiabatic speedup by pulse control. Here, we select the single-component control of qubits, resembling the ubiquitous two-level Landau-Zener problem for gate operation. We aim at obtaining fast and robust digital pulses by combining the STA and DRL algorithm. In particular, we find that DRL leads to robust digital quantum control with the operation time bounded by quantum speed limits dictated by STA. In addition, we demonstrate that robustness against systematic errors can be achieved by DRL without any input from STA. Our results introduce a general framework of digital quantum control, leading to a promising enhancement in quantum information processing.
Noisy intermediate-scale quantum computers hold the promise of tackling complex and otherwise intractable computational challenges through the massive parallelism offered by qubits. Central to realizing the potential of quantum computing are perfect entangling (PE) two-qubit gates, which serve as a critical building block for universal quantum computation. In the context of quantum optimal control, shaping electromagnetic pulses to drive quantum gates is crucial for pushing gate performance toward theoretical limits. In this work, we leverage reinforcement learning (RL) techniques to discover near-optimal pulse shapes that yield PE gates. A collection of RL agents is trained within robust simulation environments, enabling the identification of effective control strategies even under noisy conditions. Selected agents are then validated on higher-fidelity simulations, illustrating how RL-based methods can reduce calibration overhead when compared to quantum optimal control techniques. Furthermore, the RL approach is hardware agnostic with the potential for broad applicability across various quantum computing platforms.
Abstract One of the challenging tasks in quantum control is to manipulate quantum systems with high fidelity and as fast as possible. Simulated Raman shortcuts to adiabatic passage with invariant-based optimal control is an efficient technique accurately used to transfer population between two quantum states in three-level systems. This technique requires tuning parameters continuously which results in analog quantum control. However, a digital quantum controller design is of great importance in the era of digital quantum computing. Here, we use deep reinforcement learning to obtain digital Stokes and pump fields that can realize fast and accurate population transfer between states with the same parity in the three-level Λ configuration. We find that deep reinforcement learning follows exactly theshortcuts to adiabaticity (STA) based on dynamical invariant and leads to a robust population transfer against systematic errors and dephasing. This is a promising enhancement in digital quantum information processing.
Quantum control requires high-precision and robust control pulses to ensure optimal system performance. However, control sequences generated with a system model may suffer from model bias, leading to low fidelity. While model-free reinforcement learning (RL) methods have been developed to avoid such biases, training an RL agent from scratch can be time-consuming, often taking hours to gather enough samples for convergence. This challenge has hindered the broad application of RL techniques to larger and more complex quantum control issues, limiting their adaptability. In this work, we use Reinforcement Learning from Demonstration (RLfD) to leverage the control sequences generated with system models and further optimize them with RL to avoid model bias. By avoiding learning from scratch and starting with reasonable control pulse shapes, this approach can increase sample efficiency by reducing the number of samples, which can significantly reduce the training time. Thus, this method can effectively handle pulse shapes that are discretized into more than 1000 pieces without compromising final fidelity. We have simulated the preparation of several high-fidelity non-classical states using the RLfD method. We also find that the training process is more stable when using RLfD. In addition, this method is suitable for fast gate calibration using reinforcement learning.