This paper proposes a quantum neural network (QNN)-based reinforcement learning (RL) controller for the real-time control of DC–DC buck converters supplying constant power loads (CPLs). Unlike conventional RL approaches that rely on classical neural networks, the proposed method employs a parameterized quantum circuit to represent the control policy, enabling a compact and expressive function approximator. The QNN is implemented as a classically simulated variational quantum circuit; no physical quantum hardware or quantum computational speedup is claimed. It is trained offline using a deterministic policy gradient framework and subsequently deployed in a real-time control loop under strict sampling constraints. The proposed 36-parameter QNN actor reduces trainable parameters by 85% versus a computation-matched classical RL baseline (245 parameters), while achieving sub-millisecond settling times and near-zero steady-state error across reference tracking, load disturbance, and supply variation scenarios validated on a dSPACE DS1202 hardware platform at 100-kHz switching frequency. Small-signal stability analysis at three tested operating points confirms phase margins exceeding 30° and a gain margin that is theoretically infinite at those points, as the linearized phase does not cross −180°. The results highlight the ability of the QNN to capture complex system dynamics with fewer trainable parameters while maintaining stable closed-loop operation, providing, to the best of the authors’ knowledge, a first step toward integrating quantum machine learning concepts into real-time power electronics control.
This paper proposes a quantum neural network (QNN)-based reinforcement learning (RL) controller for the real-time control of DC–DC buck converters supplying constant power loads (CPLs). Unlike conventional RL approaches that rely on classical neural networks, the proposed method employs a parameterized quantum circuit to represent the control policy, enabling a compact and expressive function approximator. The QNN is implemented as a classically simulated variational quantum circuit; no physical quantum hardware or quantum computational speedup is claimed. It is trained offline using a deterministic policy gradient framework and subsequently deployed in a real-time control loop under strict sampling constraints. The proposed 36-parameter QNN actor reduces trainable parameters by 85% versus a computation-matched classical RL baseline (245 parameters), while achieving sub-millisecond settling times and near-zero steady-state error across reference tracking, load disturbance, and supply variation scenarios validated on a dSPACE DS1202 hardware platform at 100-kHz switching frequency. Small-signal stability analysis at three tested operating points confirms phase margins exceeding 30° and a gain margin that is theoretically infinite at those points, as the linearized phase does not cross −180°. The results highlight the ability of the QNN to capture complex system dynamics with fewer trainable parameters while maintaining stable closed-loop operation, providing, to the best of the authors’ knowledge, a first step toward integrating quantum machine learning concepts into real-time power electronics control.
We present a novel approach integrating quantum neural networks with reinforcement learning (RL) for house air conditioning control. Our framework employs a quantum deep Q-network (QDQN) RL implemented with PennyLane, leveraging parameterized variational quantum circuits (VQC) as function approximators for Q-values. The agent interacts with simulated indoor thermodynamic modelling, incorporating thermal capacity, heat transfer, and outdoor temperature variations. The action space consists of discrete air conditioning power levels, and the reward function balances comfort, energy, and switching penalties. To stabilize training, we introduce a target network, experience replay, and epsilon-greedy exploration. QDQN encodes the state vector into quantum rotations and applies multi-layer entangling gates, providing a potentially richer representation of the environment compared to classical networks. The QDQN agent uses VQC architecture. It incorporates data re-uploading, parameterized rotations, and strongly entangled qubits to effectively capture inter-feature correlations. We demonstrate the algorithm on episodes with outdoor conditions in both winter and summer conditions, showing convergence to policies that maintain indoor temperatures within setpoint bounds with zero violation rate. To validate the framework in a real-world noise setting, the quantum pipeline is simulated on the IBM Marrakesh system, featuring a 156-qubit Heron r2 processor with a median two-qubit (CZ) error of approximately 2.59 × 10− 3. Our results highlight the promise of quantum RL for real-world controls.
Attitude control is vital for ensuring flight stability in aircraft operating under dynamic disturbances such as turbulence and vortices. While reinforcement learning (RL)-based controllers offer adaptivity to uncertain dynamics, their deployment on airborne platforms is often constrained by the large number of training parameters and associated computational overhead. To address this limitation, this article implements a quantum reinforcement learning (QRL)-based attitude controller in which a quantum neural network (QNN) replaces the classical neural network (NN) within an actor-critic framework. Exploiting quantum principles such as superposition and entanglement, the QRL controller reduces training parameters, thereby enhancing computational efficiency and enabling resilient, lightweight flight control for next-generation aircraft systems. The proposed controller is evaluated in a simulated flight-control environment that reflects the aerodynamic specifications of a Boeing B777-300X airframe and is subjected to stochastic vortical disturbances. The simulation results demonstrate that the QNN-based controller can reduce the number of training parameters by approximately 760x compared with a controller based on the classical NN. These results indicate that, within the realistic experimental setting, QRL can provide a parameter-efficient and computationally lightweight alternative for aircraft attitude control under uncertain aerodynamic conditions.
This paper presents an engineering design framework for integrating Variational Quantum Circuits (VQCs) into industrial control systems via real-time quantum emulation on embedded hardware. In this work, we present a novel framework for fully embedded real-time quantum machine learning (QML), in which a four-qubit, four-layer VQC is both emulated and trained in situ on an FPGA-based embedded platform (dSPACE MicroLabBox 1202). The system achieves deterministic microsecond-scale response at a closed-loop frequency of 100 kHz, enabling its application in latency-critical control tasks. We demonstrate the feasibility of online VQC training within this architecture by approximating nonlinear functions in real time, thereby validating the potential of embedded QML for advanced signal processing and control applications. This approach provides a scalable and practical path toward real-time Quantum Reinforcement Learning (QRL) and other quantum-enhanced embedded controllers. The results validate the feasibility of real-time quantum emulation and establish a structured engineering design methodology for implementing trainable quantum machine learning (QML) models on embedded platforms, thereby enabling the development of deployable quantum-enhanced controllers.
Global supply chains are increasingly automated, instrumented, and interconnected creating opportunities for real-time optimization but also novel, rapidly evolving security threats (tampering, insider fraud, diversion, adversarial manipulation of sensors and models). Reinforcement learning (RL) has emerged as a powerful paradigm for sequential decision making in dynamic supply-chain environments, enabling adaptive routing, anomaly response, and recovery actions. Simultaneously, quantum neural networks (QNNs) and other hybrid quantum-classical components promise richer representations and novel algorithmic primitives that may enhance sample efficiency, combinatorial search, and kernel expressivity in data-scarce or adversarial settings. This paper integrates these two frontiers and presents a comprehensive treatment of RL–QNN hybrid architectures tailored for real-time supply-chain security. We provide (1) formal problem definitions and threat models, (2) theoretical and practical descriptions of hybrid RL–QNN designs (policy/value parameterizations, quantum feature maps, gradient estimation), (3) reproducible training algorithms and pseudocode, (4) evaluation and adversarial robustness frameworks, (5) deployment and MLOps guidance for latency-bound environments, and (6) a detailed research roadmap prioritizing near-term hybrid pilots and longer-term fault-tolerant ambitions. We ground the discussion in recent literature on QNNs, variational quantum algorithms, quantum reinforcement learning, and RL for supply chains (Cerezo et al., 2021; Havlíček et al., 2019; Meyer et al., 2024; Yan, 2022; Correll et al., 2023). Practical recommendations emphasize measurable security outcomes, reproducibility, and interpretable governance.
This paper presents a sample-efficient hybrid quantum-classical reinforcement learning (QCRL) framework for multi-objective transmission switching (MO-TS) in power systems. We introduce a Chunk-Based Data Reuploading Variational Quantum Circuit (CBDR-VQC) architecture, which is designed to enhance policy expressivity without increasing circuit depth or width. Unlike conventional VQC approaches that scale circuit size to improve learning capacity, often at the cost of hardware feasibility and trainability, our method encodes high-dimensional input features sequentially into a fixed-width, shallow quantum circuit with a learnable measurement scheme. This design maintains compatibility with near-term quantum devices while avoiding issues such as noise accumulation and barren plateaus. Embedded within a quantum-classical Soft Actor-Critic (QCSAC) framework, the proposed model achieves competitive performance for MO-TS on the IEEE 118-bus system. It significantly reduces the numbers of both required qubits and trainable parameters compared to both classical and wider VQC-based baselines, demonstrating its promise for resourceconstrained QCRL in real-world power system optimization.
This paper presents a novel Lyapunov-Based Quantum Reinforcement Learning (LQRL) framework that integrates quantum policy optimization with Lyapunov stability analysis for continuous-time vehicle control. The proposed approach combines the representational power of variational quantum circuits (VQCs) with a stability-aware policy gradient mechanism to ensure asymptotic convergence and safe decision-making under dynamic environments. The vehicle longitudinal control problem was formulated as a continuous-state reinforcement learning task, where the quantum policy network generates control actions subject to Lyapunov stability constraints. Simulation experiments were conducted in a closed-loop adaptive cruise control scenario using a quantum-inspired policy trained under stability feedback. The results demonstrate that the LQRL framework successfully embeds Lyapunov stability verification into quantum policy learning, enabling interpretable and stability-aware control performance. Although transient overshoot and Lyapunov divergence were observed under aggressive acceleration, the system maintained bounded state evolution, validating the feasibility of integrating safety guarantees within quantum reinforcement learning architectures. The proposed framework provides a foundational step toward provably safe quantum control in autonomous systems and hybrid quantum-classical optimization domains.