Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2501.16243 · Communications in computer and information science

Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach

Yang Xu, Vaneet Aggarwal

Published Jan 1, 2026• 1 citation
arXivHTMLPDF
DOI
10.1007/978-981-95-7829-0_7

Related papers

Advanced Quantum Policy Approximation in Policy Gradient Reinforcement Learning

Leonhard Kunczik

Springer eBooks•Jan 1, 2022•0 citations

Quantum reinforcement learning via policy iteration

El Amine Cherrat, Iordanis Kerenidis, Anupam Prakash

arXiv:2203.01889•Quantum Machine Intelligence•Jul 19, 2023•31 citations

Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning

Nico Meyer, Daniel D. Scherer, Axel Plinge +2 more

Reinforcement learning is a growing field in AI with a lot of potential. Intelligent behavior is learned automatically through trial and error in interaction with the environment. However, this learning process is often costly. Using variational quantum circuits as function approximators potentially can reduce this cost. In order to implement this, we propose the quantum natural policy gradient (QNPG) algorithm - a second-order gradient-based routine that takes advantage of an efficient approximation of the quantum Fisher information matrix. We experimentally demonstrate that QNPG outperforms first-order based training on different Contextual Bandits environments regarding convergence speed and stability and moreover reduces the sample complexity. Furthermore, we provide evidence for the practical feasibility of our approach by training on a 12-qubit hardware device.

arXiv:2304.13571•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 17, 2023•10 citations

Lyapunov-Aware Quantum-Inspired Reinforcement Learning for Continuous-Time Vehicle Control: A Feasibility Study

Nutkritta Kraipatthanapong, Natthaphat Thathong, Pannita Suksawas +4 more

This paper presents a novel Lyapunov-Based Quantum Reinforcement Learning (LQRL) framework that integrates quantum policy optimization with Lyapunov stability analysis for continuous-time vehicle control. The proposed approach combines the representational power of variational quantum circuits (VQCs) with a stability-aware policy gradient mechanism to ensure asymptotic convergence and safe decision-making under dynamic environments. The vehicle longitudinal control problem was formulated as a continuous-state reinforcement learning task, where the quantum policy network generates control actions subject to Lyapunov stability constraints. Simulation experiments were conducted in a closed-loop adaptive cruise control scenario using a quantum-inspired policy trained under stability feedback. The results demonstrate that the LQRL framework successfully embeds Lyapunov stability verification into quantum policy learning, enabling interpretable and stability-aware control performance. Although transient overshoot and Lyapunov divergence were observed under aggressive acceleration, the system maintained bounded state evolution, validating the feasibility of integrating safety guarantees within quantum reinforcement learning architectures. The proposed framework provides a foundational step toward provably safe quantum control in autonomous systems and hybrid quantum-classical optimization domains.

arXiv:2510.18852•Oct 21, 2025•0 citations

Reinforcement Learning for Quantum Control

Barry C. Sanders, Pantita Palittapongarnpim, Seyed Shakib Vedaie

Bulletin of the American Physical Society•Mar 7, 2018•0 citations

Continuous Quantum Reinforcement Learning for Robot Navigation

Theodora-Augustina Drăgan, Alexander Künzner, Robert Wille +1 more

One of the multiple facets of quantum reinforcement learning (QRL) is enhancing reinforcement learning (RL) algorithms with quantum submodules, namely with variational quantum circuits (VQC) as function approx-imators. QRL solutions are empirically proven to require fewer training iterations or adjustable parameters than their classical counterparts, but are usually restricted to applications that have a discrete action space and thus limited industrial relevance. We propose a hybrid quantum-classical (HQC) deep deterministic policy gradient (DDPG) approach for a robot to navigate through a maze using continuous states, continuous actions and using local observations from the robot’s LiDAR sensors. We show that this HQC method can lead to models of comparable test results to the neural network (NN)-based DDPG algorithm, that need around 200 times fewer weights. We also study the scalability of our solution with respect to the number of VQC layers and qubits, and find that in general results improve as the layer and qubit counts increase. The best rewards among all similarly sized HQC and classical DDPG methods correspond to a VQC of 8 qubits and 5 layers with no other NN. This work is another step towards continuous QRL, where literature has been sparse.

International Conference on Agents and Artificial Intelligence (ICAART)•Jan 1, 2025•1 citation
Reinforcement learning is a growing field in AI with a lot of potential. Intelligent behavior is learned automatically through trial and error in interaction with the environment. However, this learning process is often costly. Using variational quantum circuits as function approximators potentially can reduce this cost. In order to implement this, we propose the quantum natural policy gradient (QNPG) algorithm - a second-order gradient-based routine that takes advantage of an efficient approximation of the quantum Fisher information matrix. We experimentally demonstrate that QNPG outperforms first-order based training on different Contextual Bandits environments regarding convergence speed and stability and moreover reduces the sample complexity. Furthermore, we provide evidence for the practical feasibility of our approach by training on a 12-qubit hardware device.
This paper presents a novel Lyapunov-Based Quantum Reinforcement Learning (LQRL) framework that integrates quantum policy optimization with Lyapunov stability analysis for continuous-time vehicle control. The proposed approach combines the representational power of variational quantum circuits (VQCs) with a stability-aware policy gradient mechanism to ensure asymptotic convergence and safe decision-making under dynamic environments. The vehicle longitudinal control problem was formulated as a continuous-state reinforcement learning task, where the quantum policy network generates control actions subject to Lyapunov stability constraints. Simulation experiments were conducted in a closed-loop adaptive cruise control scenario using a quantum-inspired policy trained under stability feedback. The results demonstrate that the LQRL framework successfully embeds Lyapunov stability verification into quantum policy learning, enabling interpretable and stability-aware control performance. Although transient overshoot and Lyapunov divergence were observed under aggressive acceleration, the system maintained bounded state evolution, validating the feasibility of integrating safety guarantees within quantum reinforcement learning architectures. The proposed framework provides a foundational step toward provably safe quantum control in autonomous systems and hybrid quantum-classical optimization domains.
One of the multiple facets of quantum reinforcement learning (QRL) is enhancing reinforcement learning (RL) algorithms with quantum submodules, namely with variational quantum circuits (VQC) as function approx-imators. QRL solutions are empirically proven to require fewer training iterations or adjustable parameters than their classical counterparts, but are usually restricted to applications that have a discrete action space and thus limited industrial relevance. We propose a hybrid quantum-classical (HQC) deep deterministic policy gradient (DDPG) approach for a robot to navigate through a maze using continuous states, continuous actions and using local observations from the robot’s LiDAR sensors. We show that this HQC method can lead to models of comparable test results to the neural network (NN)-based DDPG algorithm, that need around 200 times fewer weights. We also study the scalability of our solution with respect to the number of VQC layers and qubits, and find that in general results improve as the layer and qubit counts increase. The best rewards among all similarly sized HQC and classical DDPG methods correspond to a VQC of 8 qubits and 5 layers with no other NN. This work is another step towards continuous QRL, where literature has been sparse.