aqora

An efficient and scalable variational quantum circuits approach for deep reinforcement learning

Níyazí Furkan Bar, Hasan Yetış, Mehmet Karaköse

Quantum Information ProcessingAug 2, 202319 citations

Architectural Influence on Variational Quantum Circuits in Multi-Agent Reinforcement Learning: Evolutionary Strategies for Optimization

Michael Kölle, Karola Schneider, Sabrina Egger +5 more

arXiv:2407.20739Lecture notes in computer scienceJan 1, 20251 citation

Diagnosing the quantum performance gap in reinforcement learning: An explainability framework for identifying structural limitations of variational quantum circuits

Basil M. Alzboun, Bilal H. Abed-alguni

Information SciencesAug 17, 20260 citations

Variational Quantum Reinforcement Learning for Quantum Control

Haixu Yu, Lei Ye, Peng Wang

IEEE International Conference on Cybernetics (CYBCONF)Apr 1, 20260 citations

Quantum Reinforcement Learning by Adaptive Non-Local Observables

Hsin-Yi Lin, Samuel Yen-Chi Chen, Huan-Hsin Tseng +1 more

Hybrid quantum-classical frameworks leverage quantum computing for machine learning; however, variational quantum circuits (VQCs) are limited by 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, ANOVQC 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.Hybrid quantum-classical frameworks leverage quantum computing for machine learning; however, variational quantum circuits (VQCs) are limited by 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, ANOVQC 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.

IEEE International Conference on Quantum Computing and Engineering (QCE)Aug 30, 20253 citations

Reinforcement learning for quantum circuit optimization

Thomas Fösel, Murphy Yuezhen Niu, Florian Marquardt +1 more

Bulletin of the American Physical SocietyMar 16, 20210 citations

Quantum Reinforcement Learning with Adaptive Variational Quantum Circuits

Related papers

Quantum Reinforcement Learning with Adaptive Variational Quantum Circuits

Related papers