On Quantum Natural Policy Gradients

Abstract

This research delves into the role of the quantum Fisher Information Matrix (FIM) in enhancing the performance of Parameterized Quantum Circuit (PQC)-based reinforcement learning agents. While previous studies have highlighted the effectiveness of PQC-based policies preconditioned with the quantum FIM in contextual bandits, its impact in broader reinforcement learning contexts, such as Markov Decision Processes, is less clear. Through a detailed analysis of L\"owner inequalities between quantum and classical FIMs, this study uncovers the nuanced distinctions and implications of using each type of FIM. Our results indicate that a PQC-based agent using the quantum FIM without additional insights typically incurs a larger approximation error and does not guarantee improved performance compared to the classical FIM. Empirical evaluations in classic control benchmarks suggest even though quantum FIM preconditioning outperforms standard gradient ascent, in general it is not superior to class

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keysequeira2024on

Related papers

• Quantum Natural Policy Gradients: Towards Sample-efficient Reinforcement Learning (2023)7.16
• Quantum Policy Iteration Via Amplitude Estimation And Grover Search -- Towards Quantum Advantage For Reinforcement Learning (2022)0.00
• Trainability Issues In Quantum Policy Gradients (2024)0.00
• Accelerating Quantum Reinforcement Learning With A Quantum Natural Policy Gradient Based Approach (2025)0.00
• From Classical Data To Quantum Advantage -- Quantum Policy Evaluation On Quantum Hardware (2025)0.00
• Hybrid Quantum-classical Policy Gradient For Adaptive Control Of Cyber-physical Systems: A Comparative Study Of VQC Vs. MLP (2025)0.00
• Quantum Policy Gradient Algorithm With Optimized Action Decoding (2022)0.00
• Robustness And Generalization In Quantum Reinforcement Learning Via Lipschitz Regularization (2024)0.00