The Quantum Control Hierarchy: When Physics-Informed Design Meets Machine Learning

• URL: http://arxiv.org/abs/2509.12832v2
• Date: Fri, 19 Sep 2025 09:52:57 GMT
• Title: The Quantum Control Hierarchy: When Physics-Informed Design Meets Machine Learning
• Authors: Atta ur Rahman, M. Y. Abd-Rabbou, Cong-feng Qiao,
• Abstract summary: We address a wide spectrum of quantum control strategies, including various open-loop protocols and advanced adaptive methods.<n>For entanglement preservation, a physics-informed hybrid Quantum Error Correction and Dynamical Decoupling protocol provides the most stable and effective solution.<n>For dynamic tasks requiring the discovery of non-trivial control sequences, such as DD, Floquet engineering, and rapid entanglement generation or coherent transport, the model-free Reinforcement Learning agents consistently find superior solutions.
• Score: 0.6053648545114841
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address a wide spectrum of quantum control strategies, including various open-loop protocols and advanced adaptive methods. These methodologies apply to few-qubit scenarios and naturally scale to larger N-qubit systems. We benchmark them across fundamental quantum tasks: entanglement preservation/generation, and directed quantum transport in a disordered quantum walk. All simulations are performed in a challenging environment featuring non-Markov colored noise, imperfections, and the Markov Lindblad equation. With a complex task-dependent performance hierarchy, our deterministic protocols proved highly effective for entanglement generation/preservation, and in specific pulse configurations, they even outperformed the RL-optimization. In contrast, more advanced methods demonstrate a marked specialization. For entanglement preservation, a physics-informed hybrid Quantum Error Correction and Dynamical Decoupling (QEC-DD) protocol provides the most stable and effective solution, outperforming all other approaches. Conversely, for dynamic tasks requiring the discovery of non-trivial control sequences, such as DD, Floquet engineering, and rapid entanglement generation or coherent transport, the model-free Reinforcement Learning (RL) agents consistently find superior solutions. We further demonstrate that the control pulse envelope is a non-trivial factor that actively shapes the control landscape, which determines the difficulty for all protocols and highlights the adaptability of the RL agent. We conclude that no single strategy is universally dominant. A clear picture emerges: the future of high-fidelity quantum control lies in a synthesis of physics-informed design, as exemplified by robust hybrid methods, and the specialized, high-performance optimization power of adaptive machine learning.

Related papers

• Learning to steer quantum many-body dynamics with tree optimization [7.777344558557047]
  We present an AI framework that learns to design pulse sequences for optimized quantum control over many-body spin systems.<n>Our framework identifies over 900 high-performing sequences that exhibit non-intuitive structures.<n>Experiments in a diamond spin ensemble show that the best AI-designed sequences achieve coherence times exceeding 200 microseconds.
  arXiv  Detail & Related papers  (2025-10-09T05:30:12Z)
• Reinforcement Learning for Quantum Network Control with Application-Driven Objectives [53.03367590211247]
  Dynamic programming and reinforcement learning offer promising tools for optimizing control strategies.<n>We propose a novel RL framework that directly optimize non-linear, differentiable objective functions.<n>Our work comprises the first step towards non-linear objective function optimization in quantum networks with RL, opening a path towards more advanced use cases.
  arXiv  Detail & Related papers  (2025-09-12T18:41:10Z)
• Provably Robust Training of Quantum Circuit Classifiers Against Parameter Noise [49.97673761305336]
  Noise remains a major obstacle to achieving reliable quantum algorithms.<n>We present a provably noise-resilient training theory and algorithm to enhance the robustness of parameterized quantum circuit classifiers.
  arXiv  Detail & Related papers  (2025-05-24T02:51:34Z)
• Hardware Co-Designed Optimal Control for Programmable Atomic Quantum Processors via Reinforcement Learning [0.18416014644193068]
  We introduce a hardware co-designed quantum control framework to address inherent imperfections in classical control hardware.<n>We demonstrate that the proposed framework enables robust, high-fidelity parallel single-qubit gate operations.<n>We find that while PPO performance degrades as system complexity increases, the end-to-end differentiable RL consistently achieves gate fidelities above 99.9$%$.
  arXiv  Detail & Related papers  (2025-04-16T03:30:40Z)
• Controlling nonergodicity in quantum many-body systems by reinforcement learning [0.0]
  We develop a model-free and deep-reinforcement learning framework for quantum nonergodicity control.<n>We use the paradigmatic one-dimensional tilted Fermi-Hubbard system to demonstrate that the DRL agent can efficiently learn the quantum many-body system.<n>The continuous control protocols and observations are experimentally feasible.
  arXiv  Detail & Related papers  (2024-08-21T20:55:44Z)
• Quantum control by the environment: Turing uncomputability, Optimization over Stiefel manifolds, Reachable sets, and Incoherent GRAPE [56.47577824219207]
  In many practical situations, the controlled quantum systems are open, interacting with the environment. In this note, we briefly review some results on control of open quantum systems using environment as a resource.
  arXiv  Detail & Related papers  (2024-03-20T10:09:13Z)
• Quantum Gate Optimization for Rydberg Architectures in the Weak-Coupling Limit [55.05109484230879]
  We demonstrate machine learning assisted design of a two-qubit gate in a Rydberg tweezer system. We generate optimal pulse sequences that implement a CNOT gate with high fidelity. We show that local control of single qubit operations is sufficient for performing quantum computation on a large array of atoms.
  arXiv  Detail & Related papers  (2023-06-14T18:24:51Z)
• Direct pulse-level compilation of arbitrary quantum logic gates on superconducting qutrits [36.30869856057226]
  We demonstrate any arbitrary qubit and qutrit gate can be realized with high-fidelity, which can significantly reduce the length of a gate sequence. We show that optimal control gates are robust to drift for at least three hours and that the same calibration parameters can be used for all implemented gates.
  arXiv  Detail & Related papers  (2023-03-07T22:15:43Z)
• Multi-squeezed state generation and universal bosonic control via a driven quantum Rabi model [68.8204255655161]
  Universal control over a bosonic degree of freedom is key in the quest for quantum-based technologies. Here we consider a single ancillary two-level system, interacting with the bosonic mode of interest via a driven quantum Rabi model. We show that it is sufficient to induce the deterministic realization of a large class of Gaussian and non-Gaussian gates, which in turn provide universal bosonic control.
  arXiv  Detail & Related papers  (2022-09-16T14:18:53Z)
• Optimal steering of matrix product states and quantum many-body scars [0.0]
  We formulate an approach to control quantum systems based on matrix product states(MPS) We compare counter-diabatic and leakage minimization approaches to the so-called local steering problem. We find that the leakage-based approach generally outperforms the counter-diabatic framework.
  arXiv  Detail & Related papers  (2022-04-06T15:34:27Z)
• Dynamical learning of a photonics quantum-state engineering process [48.7576911714538]
  Experimentally engineering high-dimensional quantum states is a crucial task for several quantum information protocols. We implement an automated adaptive optimization protocol to engineer photonic Orbital Angular Momentum (OAM) states. This approach represents a powerful tool for automated optimizations of noisy experimental tasks for quantum information protocols and technologies.
  arXiv  Detail & Related papers  (2022-01-14T19:24:31Z)
• Protocol Discovery for the Quantum Control of Majoranas by Differentiable Programming and Natural Evolution Strategies [0.0]
  We applyDP andNES to the optimal transport of Majorana zero modes in superconducting nanowires. We identify efficient but strikingly counter-intuitive motion strategies in the non-adiabatic regime. Our results demonstrate that machine learning for quantum control can be applied efficiently to quantum many-body dynamical systems.
  arXiv  Detail & Related papers  (2020-08-20T18:00:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.