Hybrid control of uncertain quantum systems via fuzzy estimation and quantum reinforcement learning

Michèle Desouter-Lecomte

Chunlin Chen, Jiang Frank, Daoyi Dong

A hybrid control approach for uncertain quantum systems is proposed using probabilistic fuzzy estimators (PFE) and quantum reinforcement learning (QRL). This hybrid control design involves coherent control with PFE and learning control via QRL. The problems of controlling a quantum system from an initial state to a pointed target state are studied in this paper, where we assume that the initial quantum state is a mixed state and the target quantum state is a controllable pure state within a wavefunction controllable subspace. First, the initial quantum system is controlled coherently with the help of a PFE. When the controlled system is estimated to be likely to collapse to an expected eigen state, trigger the measurement and the quantum system collapses to an eigen state in the wavefuntion controllable subspace with a high probability. Then the quantum system is driven to the target state with admissible controls, where the control sequence is learned and optimized with QRL. An example is presented and analyzed to demonstrate the control process.

Javier Lazaro, Juan-Ignacio Vazquez, Pablo Garcia-Bringas

Parameterised quantum circuit (PQC) based Quantum Reinforcement Learning (QRL) has emerged as a promising paradigm at the intersection of quantum computing and reinforcement learning (RL). By design, PQCs create hybrid quantum-classical models, but their practical applicability remains uncertain due to training instabilities, barren plateaus (BPs), and the difficulty of isolating the contribution of individual pipeline components. In this work, we dissect PQC based QRL architectures through a systematic experimental evaluation of three aspects recurrently identified as critical: (i) data embedding strategies, with Data Reuploading (DR) as an advanced approach; (ii) ansatz design, particularly the role of entanglement; and (iii) post-processing blocks after quantum measurement, with a focus on the underexplored Output Reuse (OR) technique. Using a unified PPO-CartPole framework, we perform controlled comparisons between hybrid and classical agents under identical conditions. Our results show that OR, though purely classical, exhibits distinct behaviour in hybrid pipelines, that DR improves trainability and stability, and that stronger entanglement can degrade optimisation, offsetting classical gains. Together, these findings provide controlled empirical evidence of the interplay between quantum and classical contributions, and establish a reproducible framework for systematic benchmarking and component-wise analysis in QRL.

Barry C. Sanders, Pantita Palittapongarnpim, Seyed Shakib Vedaie

Gyu Seon Kim, Jaehyun Chung, Soohyun Park +3 more

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.

Ming-Zhong Ai, Yongcheng Ding, Yue Ban +7 more