Neural Architecture Search (NAS) involves exploring large and combinatorial search spaces, for which numerous approaches have been proposed, including reinforcement learning, evolutionary algorithms, Bayesian optimization, and gradient-based methods among others. Despite these advances, efficient exploration remains a key challenge, particularly as the search space scales combinatorially. Motivated by prior work based on Q-learning strategies, which are limited in large spaces, this work investigates a Quantum Reinforcement Learning (QRL) framework based on probabilistic policy optimization. We propose a QRL approach where a parameterized quantum circuit represents a policy over candidate architectures, and is trained to maximize the expected reward defined by validation accuracy. This method is compared against two baselines: Random Search and a Classical Reinforcement Learning approach using policy gradient with a Bernoulli distribution. All methods are evaluated under identical budgets using the NATS-Bench benchmark, enabling efficient and controlled comparison without full model training. The results demonstrate that both QRL and Classical RL learn meaningful search policies, consistently outperforming Random Search. QRL achieves competitive performance with respect to Classical RL, confirming its ability to effectively explore the architecture space. We further analyze the impact of key hyperparameters to identify practical trade-offs between accuracy, model complexity, and computational cost. Overall, the results demonstrate that QRL is a viable approach for discrete architecture search, capable of learning effective policies in large combinatorial spaces, while indicating clear directions for improving its efficiency and scalability. ... Read more

Recent advances in quantum photonics and single-photon detection are enabling new sensing capabilities for vibration-based diagnostics and non-destructive evaluation. This work investigates the signal characteristics and effective resolution of the Quantum Photonic Vibrometer (QPV), a quantum-enhanced, non-contact sensor designed for sub-nanometric vibration measurements in Structural Health Monitoring (SHM). The QPV operates at a telecom wavelength of 1550 nm using a mode-locked laser emitting 20 MHz optical pulses, combined with time-gated photon detection on an avalanche photodiode (APD). The measured photon-count signal arises from phase-induced speckle modulation, where structural vibrations modulate the optical phase of the backscattered field, producing measurable intensity fluctuations. In this study, photon-count time series obtained from aluminum specimens (pure and with artificial defects) are analyzed using time- and frequency-domain techniques, including Fast Fourier Transform (FFT), sliding Root Mean Square (RMS), variance, and Hilbert envelope extraction. A simplified physical model is introduced to relate photon-count fluctuations to vibration-induced phase variations, providing insight into the effective measurement resolution in the presence of photon shot noise. Results show that pure aluminum exhibits stable and low-variance responses with consistent spectral signatures, while defective samples introduce measurable changes in frequency content and signal variability. These observations indicate that the QPV signal contains physically meaningful information related to structural condition, and that its sensitivity is governed by the interplay between speckle-induced phase modulation and photon-count statistics. This work highlights the potential of QPV as a sensing modality for vibration analysis and defect-sensitive diagnostics, establishing a foundation for data-driven structural health monitoring using quantum-enhanced vibrometry. ... Read more