Quantum Reinforcement Learning by Adaptive Non-local Observables
Abstract
Hybrid quantum-classical frameworks leverage quantum computing for machine learning; however, variational quantum circuits (VQCs) are limited by the need for local measurements. We introduce an adaptive non-local observable (ANO) paradigm within VQCs for quantum reinforcement learning (QRL), jointly optimizing circuit parameters and multi-qubit measurements. The ANO-VQC architecture serves as the function approximator in Deep Q-Network (DQN) and Asynchronous Advantage Actor-Critic (A3C) algorithms. On multiple benchmark tasks, ANO-VQC agents outperform baseline VQCs. Ablation studies reveal that adaptive measurements enhance the function space without increasing circuit depth. Our results demonstrate that adaptive multi-qubit observables can enable practical quantum advantages in reinforcement learning.
Cite
@article{arxiv.2507.19629,
title = {Quantum Reinforcement Learning by Adaptive Non-local Observables},
author = {Hsin-Yi Lin and Samuel Yen-Chi Chen and Huan-Hsin Tseng and Shinjae Yoo},
journal= {arXiv preprint arXiv:2507.19629},
year = {2025}
}
Comments
Accepted at IEEE Quantum Week 2025 (QCE 2025)