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.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keylin2025quantum

Related papers

• Efficient Quantum Recurrent Reinforcement Learning Via Quantum Reservoir Computing (2023)0.00
• Hybrid Quantum-classical Policy Gradient For Adaptive Control Of Cyber-physical Systems: A Comparative Study Of VQC Vs. MLP (2025)0.00
• Variational Quantum Circuits For Deep Reinforcement Learning (2019)19.19
• An Introduction To Quantum Reinforcement Learning (QRL) (2024)0.00
• Hybrid Quantum-classical Algorithm For Near-optimal Planning In Pomdps (2025)0.00
• Auxiliary Task-based Deep Reinforcement Learning For Quantum Control (2023)5.84
• Vqc-based Reinforcement Learning With Data Re-uploading: Performance And Trainability (2024)8.60
• MADQRL: Distributed Quantum Reinforcement Learning Framework For Multi-agent Environments (2026)0.00