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:2108.04490 · Quantum Machine Intelligence

Quantum reinforcement learning: the maze problem

Nicola Dalla Pozza, Lorenzo Buffoni, Stefano Martina, Filippo Caruso

Published May 27, 2022• 42 citations
arXivHTMLPDF

Abstract

Abstract Quantum machine learning (QML) is a young but rapidly growing field where quantum information meets machine learning. Here, we will introduce a new QML model generalising the classical concept of reinforcement learning to the quantum domain, i.e. quantum reinforcement learning (QRL). In particular, we apply this idea to the maze problem, where an agent has to learn the optimal set of actions in order to escape from a maze with the highest success probability. To perform the strategy optimisation, we consider a hybrid protocol where QRL is combined with classical deep neural networks. In particular, we find that the agent learns the optimal strategy in both the classical and quantum regimes, and we also investigate its behaviour in a noisy environment. It turns out that the quantum speedup does robustly allow the agent to exploit useful actions also at very short time scales, with key roles played by the quantum coherence and the external noise. This new framework has the high potential to be applied to perform different tasks (e.g. high transmission/processing rates and quantum error correction) in the new-generation noisy intermediate-scale quantum (NISQ) devices whose topology engineering is starting to become a new and crucial control knob for practical applications in real-world problems. This work is dedicated to the memory of Peter Wittek.

DOI
10.1007/s42484-022-00068-y

Related papers

Quantum Deep Recurrent Reinforcement Learning

Samuel Yen-Chi Chen

Recent advances in quantum computing (QC) and machine learning (ML) have drawn significant attention to the development of quantum machine learning (QML). Reinforcement learning (RL) is one of the ML paradigms which can be used to solve complex sequential decision making problems. Classical RL has been shown to be capable to solve various challenging tasks. However, RL algorithms in the quantum world are still in their infancy. One of the challenges yet to solve is how to train quantum RL in the partially observable environments. In this paper, we approach this challenge through building QRL agents with quantum recurrent neural networks (QRNN). Specifically, we choose the quantum long short-term memory (QLSTM) to be the core of the QRL agent and train the whole model with deep Q-learning. We demonstrate the results via numerical simulations that the QLSTM-DRQN can solve standard benchmark such as Cart-Pole with more stable and higher average scores than classical DRQN with similar architecture and number of model parameters.

arXiv:2210.14876•IEEE International Conference on Acoustics Speech and Signal Processing•May 5, 2023•49 citations

Challenge-Response Quantum Reinforcement Learning with Application to Quantum-Assisted Authentication

Jawaher Kaldari, Saif Al-Kuwari

Quantum reinforcement learning (QRL) has emerged as a promising research direction that integrates quantum information processing into reinforcement learning frameworks. While many existing QRL studies apply quantum agents to classical environments, it has been realized that the potential advantages of QRL are most naturally explored in environments that exhibit intrinsically quantum characteristics, where the agent's observations and interactions arise from quantum processes. In this work, we propose a quantum reinforcement learning environment formulated as a challenge-response task with hidden information. In the proposed environment, Alice encodes a classical bit into the parameters of a quantum circuit, while Bob, with a trained reinforcement learning agent, interacts with a limited number of quantum state copies to infer the hidden bit. The agent must select measurement strategies and decide when to terminate the interaction under explicit resource constraints. To study the solvability of the proposed environment, we consider three agents: a purely classical agent, a lightweight hybrid agent and a deep hybrid agent. Through experiments, we analyze the trade-off between inference accuracy and quantum resource consumption under varying interaction penalties. Our results show that the lightweight hybrid agent achieves reliable inference using as few as two quantum state copies, outperforming both the classical baseline and the deep hybrid agent across both high and low-penalty regimes. We further evaluate robustness under realistic quantum noise models and discuss the relevance of the proposed environment for security-oriented applications, including quantum-assisted authentication.

quant-pharXiv:2602.12464•Quantum Machine Intelligence•Feb 16, 2026•1 citation

Quantum Machine Learning Architecture Search via Deep Reinforcement Learning

Xin Dai, Tzu-Chieh Wei, Shinjae Yoo +1 more

The rapid advancement of quantum computing (QC) and machine learning (ML) has given rise to the burgeoning field of quantum machine learning (QML), aiming to capitalize on the strengths of quantum computing to propel ML forward. Despite its promise, crafting effective QML models necessitates profound expertise to strike a delicate balance between model intricacy and feasibility on Noisy Intermediate-Scale Quantum (NISQ) devices. While complex models offer robust representation capabilities, their extensive circuit depth may impede seamless execution on extant noisy quantum platforms. In this paper, we address this quandary of QML model design by employing deep reinforcement learning to explore proficient QML model architectures tailored for designated supervised learning tasks. Specifically, our methodology involves training an RL agent to devise policies that facilitate the discovery of QML models without predetermined ansatz. Furthermore, we integrate an adaptive mechanism to dynamically adjust the learning objectives, fostering continuous improvement in the agent's learning process. Through extensive numerical simulations, we illustrate the efficacy of our approach within the realm of classification tasks. Our proposed method successfully identifies VQC architectures capable of achieving high classification accuracy while minimizing gate depth. This pioneering approach not only advances the study of AI-driven quantum circuit design but also holds significant promise for enhancing performance in the NISQ era.

arXiv:2407.20147•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•42 citations

Autonomous Quantum System Design Using Reinforcement Learning and Evolutionary Strategies

Thirunavukarasu, Elanchezhian, Mohamed Ashraf +1 more

The design of autonomous quantum systems constitutes an entirely new paradigm for next-generation computing by having machine intelligence do the engineering work to build and optimise successful quantum architectures. We address the problem of self-optimizing quantum systems that perform adaptive control, circuit synthesis and decision making in both accurate and uncertain controllable environments via a two-pronged approach: Reinforcement Learning (RL) together with Evolutionary Strategies (ES). In this work, we find that reinforcement learning provides a general framework for sequential decision-making, where agents learn optimal policies from reward signals by interacting with quantum environments. Evolutionary strategies, which are based on ideas from biological evolution, provide an alternative to RL by performing global optimization of quantum circuit parameters and architectures using the standard canonical processes of mutation, selection and recombination. Recent developments in quantum technologies show, again, that machine learning tools (ML), especially RL can be very useful to optimize unavailable closed blow-ups related with quantity functions. Moreover, evolutionary optimization based hybrids with RL have demonstrated better performance on the complex multi-objective quantum problems due to balanced exploitation and exploration. In this paper, we provide an overview of a versatile framework for autonomous quantum system design that showcases example algorithmic architectures, hybrid machine learning models and real world applications in areas such as quantum control, quantum circuit synthesis and energy optimization. In addition, we discuss well-known obstacles such as the scalability problem, the noise sensitivity issue, barren plateaus of quantum optimization and computational complexity. Comparisons to traditional methods show that reinforcement learning (RL) when combined with evolutionary strategies enables a significant improvement in efficiency, adaptability, and robustness for quantum system design as supported by experimental studies and case analyses. Future research directions are then discussed, including quantum-native learning algorithms, multi-agent quantum reinforcement learning and hardware-aware optimization techniques

International Journal of Quantum Computing and Artificial Intelligence (IJQCAI)•Mar 29, 2026•0 citations

Noise-resilient quantum reinforcement learning

Jing-Ci Yue, Jun‐Hong An

As a branch of quantum machine learning, quantum reinforcement learning (QRL) aims to solve complex sequential decision-making problems more efficiently and effectively than its classical counterpart by exploiting quantum resources. However, in the noisy intermediate-scale quantum (NISQ) era, its realization is challenged by the ubiquitous noise-induced decoherence. Here, we propose a noise-resilient QRL scheme for a quantum eigensolver with a two-level system as an agent. By investigating the non-Markovian decoherence effect on the QRL for solving the eigenstates of the agent-environment interaction Hamiltonian, we find that the formation of a bound state in the energy spectrum of the total agent-noise system restores the QRL performance to that in the noiseless case. Providing a universal physical mechanism to suppress the decoherence effect on quantum machine learning, our result lays the foundation for designing NISQ algorithms and offers a guideline for their practical implementation.

arXiv:2508.20601•Physical Review Applied•Mar 26, 2026•0 citations

Optimization of Reinforcement Learning Using Quantum Computation

Roopa Ravish, Nischal R. Bhat, N. Nandakumar +3 more

Exploring the convergence of quantum computing and machine learning, this paper delves into Quantum Reinforcement Learning (QRL) with a specific focus on Variational Quantum Circuits (VQC). Alongside a comprehensive examination of the field, the study presents a concrete implementation of QRL tailored to foundational gym environments. Leveraging principles from Quantum Computing, experiments reveal QRL’s potential in enhancing reinforcement learning tasks within these environments, showcasing notable space optimization for RL models. Quantitative results indicate a reduction in the number of trainable parameters by up to 90% when compared to classical approaches, significantly improving efficiency, mainly due to quantum principles of superposition and entanglement. This highlights the promising implications of integrating quantum computing techniques to address challenges and advance capabilities in fundamental reinforcement learning scenarios. Furthermore, the study discusses the adaptability of QRL algorithms to diverse problem domains, suggesting their potential for scalability and applicability beyond simple environments. Such versatility underscores the robustness and practical relevance of QRL methodologies in real-world scenarios, positioning them as valuable tools for tackling complex reinforcement learning challenges.

IEEE Access•Jan 1, 2024•12 citations
Abstract Quantum machine learning (QML) is a young but rapidly growing field where quantum information meets machine learning. Here, we will introduce a new QML model generalising the classical concept of reinforcement learning to the quantum domain, i.e. quantum reinforcement learning (QRL). In particular, we apply this idea to the maze problem, where an agent has to learn the optimal set of actions in order to escape from a maze with the highest success probability. To perform the strategy optimisation, we consider a hybrid protocol where QRL is combined with classical deep neural networks. In particular, we find that the agent learns the optimal strategy in both the classical and quantum regimes, and we also investigate its behaviour in a noisy environment. It turns out that the quantum speedup does robustly allow the agent to exploit useful actions also at very short time scales, with key roles played by the quantum coherence and the external noise. This new framework has the high potential to be applied to perform different tasks (e.g. high transmission/processing rates and quantum error correction) in the new-generation noisy intermediate-scale quantum (NISQ) devices whose topology engineering is starting to become a new and crucial control knob for practical applications in real-world problems. This work is dedicated to the memory of Peter Wittek.
Recent advances in quantum computing (QC) and machine learning (ML) have drawn significant attention to the development of quantum machine learning (QML). Reinforcement learning (RL) is one of the ML paradigms which can be used to solve complex sequential decision making problems. Classical RL has been shown to be capable to solve various challenging tasks. However, RL algorithms in the quantum world are still in their infancy. One of the challenges yet to solve is how to train quantum RL in the partially observable environments. In this paper, we approach this challenge through building QRL agents with quantum recurrent neural networks (QRNN). Specifically, we choose the quantum long short-term memory (QLSTM) to be the core of the QRL agent and train the whole model with deep Q-learning. We demonstrate the results via numerical simulations that the QLSTM-DRQN can solve standard benchmark such as Cart-Pole with more stable and higher average scores than classical DRQN with similar architecture and number of model parameters.
Quantum reinforcement learning (QRL) has emerged as a promising research direction that integrates quantum information processing into reinforcement learning frameworks. While many existing QRL studies apply quantum agents to classical environments, it has been realized that the potential advantages of QRL are most naturally explored in environments that exhibit intrinsically quantum characteristics, where the agent's observations and interactions arise from quantum processes. In this work, we propose a quantum reinforcement learning environment formulated as a challenge-response task with hidden information. In the proposed environment, Alice encodes a classical bit into the parameters of a quantum circuit, while Bob, with a trained reinforcement learning agent, interacts with a limited number of quantum state copies to infer the hidden bit. The agent must select measurement strategies and decide when to terminate the interaction under explicit resource constraints. To study the solvability of the proposed environment, we consider three agents: a purely classical agent, a lightweight hybrid agent and a deep hybrid agent. Through experiments, we analyze the trade-off between inference accuracy and quantum resource consumption under varying interaction penalties. Our results show that the lightweight hybrid agent achieves reliable inference using as few as two quantum state copies, outperforming both the classical baseline and the deep hybrid agent across both high and low-penalty regimes. We further evaluate robustness under realistic quantum noise models and discuss the relevance of the proposed environment for security-oriented applications, including quantum-assisted authentication.
The rapid advancement of quantum computing (QC) and machine learning (ML) has given rise to the burgeoning field of quantum machine learning (QML), aiming to capitalize on the strengths of quantum computing to propel ML forward. Despite its promise, crafting effective QML models necessitates profound expertise to strike a delicate balance between model intricacy and feasibility on Noisy Intermediate-Scale Quantum (NISQ) devices. While complex models offer robust representation capabilities, their extensive circuit depth may impede seamless execution on extant noisy quantum platforms. In this paper, we address this quandary of QML model design by employing deep reinforcement learning to explore proficient QML model architectures tailored for designated supervised learning tasks. Specifically, our methodology involves training an RL agent to devise policies that facilitate the discovery of QML models without predetermined ansatz. Furthermore, we integrate an adaptive mechanism to dynamically adjust the learning objectives, fostering continuous improvement in the agent's learning process. Through extensive numerical simulations, we illustrate the efficacy of our approach within the realm of classification tasks. Our proposed method successfully identifies VQC architectures capable of achieving high classification accuracy while minimizing gate depth. This pioneering approach not only advances the study of AI-driven quantum circuit design but also holds significant promise for enhancing performance in the NISQ era.
The design of autonomous quantum systems constitutes an entirely new paradigm for next-generation computing by having machine intelligence do the engineering work to build and optimise successful quantum architectures. We address the problem of self-optimizing quantum systems that perform adaptive control, circuit synthesis and decision making in both accurate and uncertain controllable environments via a two-pronged approach: Reinforcement Learning (RL) together with Evolutionary Strategies (ES). In this work, we find that reinforcement learning provides a general framework for sequential decision-making, where agents learn optimal policies from reward signals by interacting with quantum environments. Evolutionary strategies, which are based on ideas from biological evolution, provide an alternative to RL by performing global optimization of quantum circuit parameters and architectures using the standard canonical processes of mutation, selection and recombination. Recent developments in quantum technologies show, again, that machine learning tools (ML), especially RL can be very useful to optimize unavailable closed blow-ups related with quantity functions. Moreover, evolutionary optimization based hybrids with RL have demonstrated better performance on the complex multi-objective quantum problems due to balanced exploitation and exploration. In this paper, we provide an overview of a versatile framework for autonomous quantum system design that showcases example algorithmic architectures, hybrid machine learning models and real world applications in areas such as quantum control, quantum circuit synthesis and energy optimization. In addition, we discuss well-known obstacles such as the scalability problem, the noise sensitivity issue, barren plateaus of quantum optimization and computational complexity. Comparisons to traditional methods show that reinforcement learning (RL) when combined with evolutionary strategies enables a significant improvement in efficiency, adaptability, and robustness for quantum system design as supported by experimental studies and case analyses. Future research directions are then discussed, including quantum-native learning algorithms, multi-agent quantum reinforcement learning and hardware-aware optimization techniques
As a branch of quantum machine learning, quantum reinforcement learning (QRL) aims to solve complex sequential decision-making problems more efficiently and effectively than its classical counterpart by exploiting quantum resources. However, in the noisy intermediate-scale quantum (NISQ) era, its realization is challenged by the ubiquitous noise-induced decoherence. Here, we propose a noise-resilient QRL scheme for a quantum eigensolver with a two-level system as an agent. By investigating the non-Markovian decoherence effect on the QRL for solving the eigenstates of the agent-environment interaction Hamiltonian, we find that the formation of a bound state in the energy spectrum of the total agent-noise system restores the QRL performance to that in the noiseless case. Providing a universal physical mechanism to suppress the decoherence effect on quantum machine learning, our result lays the foundation for designing NISQ algorithms and offers a guideline for their practical implementation.
Exploring the convergence of quantum computing and machine learning, this paper delves into Quantum Reinforcement Learning (QRL) with a specific focus on Variational Quantum Circuits (VQC). Alongside a comprehensive examination of the field, the study presents a concrete implementation of QRL tailored to foundational gym environments. Leveraging principles from Quantum Computing, experiments reveal QRL’s potential in enhancing reinforcement learning tasks within these environments, showcasing notable space optimization for RL models. Quantitative results indicate a reduction in the number of trainable parameters by up to 90% when compared to classical approaches, significantly improving efficiency, mainly due to quantum principles of superposition and entanglement. This highlights the promising implications of integrating quantum computing techniques to address challenges and advance capabilities in fundamental reinforcement learning scenarios. Furthermore, the study discusses the adaptability of QRL algorithms to diverse problem domains, suggesting their potential for scalability and applicability beyond simple environments. Such versatility underscores the robustness and practical relevance of QRL methodologies in real-world scenarios, positioning them as valuable tools for tackling complex reinforcement learning challenges.