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

Communications in computer and information science

Quantum Artificial Intelligence: Reinforcement Learning, Memory Models, and Self-programming Architectures

Samuel Yen-Chi Chen

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.1007/978-981-95-7829-0_1

Related papers

Quantum Computing &Amp; Reinforcement Learning: Partners in Achieving Artificial General Intelligence

Akintunde Agunbiade

•Jan 1, 2022•4 citations

Quantum Artificial Intelligence Architectures and Applications

Remzi Yıldırım, Furkan Sefa Demirci

International Symposium on AI-Driven Engineering Systems (ISADES)•Jun 1, 2026•0 citations

Quantum Artificial Intelligence: From Quantum Neural Networks to Self-Programming Architectures [Feature]

Samuel Yen-Chi Chen

Quantum Artificial Intelligence (QAI) represents the convergence of quantum computing and machine learning, aiming to harness the computational power of quantum mechanics to enhance the efficiency, scalability, and generalization capability of intelligent systems. This article provides a tutorial on the foundations, models, and emerging directions of QAI. We first review the core concepts of quantum information and hybrid quantum–classical computing, followed by a detailed discussion of variational quantum circuits (VQCs)—the fundamental building blocks of quantum neural networks (QNNs). Building upon these foundations, we introduce representative QAI architectures, including Quantum Convolutional Neural Networks (QCNNs) for pattern recognition, Quantum Long Short-Term Memory (QLSTM) for sequential modeling, and Quantum Reinforcement Learning (QRL) for decision making and control. Advanced topics such as Quantum Architecture Search (QAS), Quantum Fast Weight Programmers (QFWP), and the Quantum-Train (QT) framework are presented to illustrate how classical and quantum models can dynamically co-design and reprogram one another. Furthermore, we discuss federated and distributed quantum learning, encoding complexity, and training challenges such as barren plateaus and hardware constraints. The article concludes with a forward-looking outlook on scalable QAI systems, autonomous quantum agents, and the long-term vision of self-programming, distributed intelligence. By bridging quantum theory, learning algorithms, and system architectures, this work aims to offer both foundational understanding and strategic insights for the next generation of hybrid quantum-classical intelligence.

IEEE Circuits and Systems Magazine•Jan 1, 2026•2 citations

Quantum Reinforcement Learning: Advancing AI Agents Through Quantum Computing

Ved Seetohul, Hamid Jahankhani, Stefan Kendzierskyj +1 more

Space Law and Policy•Jan 1, 2024•10 citations

Model-Free Deep Recurrent Q-Network Reinforcement Learning for Quantum Circuit Architectures Design

Tomah Sogabe, Tomoaki Kimura, Chih-Chieh Chen +4 more

Artificial intelligence (AI) technology leads to new insights into the manipulation of quantum systems in the Noisy Intermediate-Scale Quantum (NISQ) era. Classical agent-based artificial intelligence algorithms provide a framework for the design or control of quantum systems. Traditional reinforcement learning methods are designed for the Markov Decision Process (MDP) and, hence, have difficulty in dealing with partially observable or quantum observable decision processes. Due to the difficulty of building or inferring a model of a specified quantum system, a model-free-based control approach is more practical and feasible than its counterpart of a model-based approach. In this work, we apply a model-free deep recurrent Q-network (DRQN) reinforcement learning method for qubit-based quantum circuit architecture design problems. This paper is the first attempt to solve the quantum circuit design problem from the recurrent reinforcement learning algorithm, while using discrete policy. Simulation results suggest that our long short-term memory (LSTM)-based DRQN method is able to learn quantum circuits for entangled Bell–Greenberger–Horne–Zeilinger (Bell–GHZ) states. However, since we also observe unstable learning curves in experiments, suggesting that the DRQN could be a promising method for AI-based quantum circuit design application, more investigation on the stability issue would be required.

Quantum Reports•Sep 21, 2022•13 citations

Brain-Inspired Agents for Quantum Reinforcement Learning

Eva Andrés, Manuel Pegalájar Cuéllar, Gabriel Navarro

In recent years, advancements in brain science and neuroscience have significantly influenced the field of computer science, particularly in the domain of reinforcement learning (RL). Drawing insights from neurobiology and neuropsychology, researchers have leveraged these findings to develop novel mechanisms for understanding intelligent decision-making processes in the brain. Concurrently, the emergence of quantum computing has opened new frontiers in artificial intelligence, leading to the development of quantum machine learning (QML). This study introduces a novel model that integrates Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, inspired by the complex workings of the human brain. Specifically designed for reinforcement learning tasks in energy-efficient environments, our approach progresses through two distinct stages mirroring sensory and memory systems. In the initial stage, analogous to the brain’s hypothalamus, low-level information is extracted to emulate sensory data processing patterns. Subsequently, resembling the hippocampus, this information is processed at a higher level, capturing and memorizing correlated patterns. We conduct a comparative analysis of our model against existing quantum models such as Quantum Neural Networks and their classical counterparts, elucidating its unique contributions. Through empirical results, we aim to underscore the effectiveness of our approach in optimizing energy consumption in practical scenarios.

Mathematics•Apr 19, 2024•8 citations
Quantum Artificial Intelligence (QAI) represents the convergence of quantum computing and machine learning, aiming to harness the computational power of quantum mechanics to enhance the efficiency, scalability, and generalization capability of intelligent systems. This article provides a tutorial on the foundations, models, and emerging directions of QAI. We first review the core concepts of quantum information and hybrid quantum–classical computing, followed by a detailed discussion of variational quantum circuits (VQCs)—the fundamental building blocks of quantum neural networks (QNNs). Building upon these foundations, we introduce representative QAI architectures, including Quantum Convolutional Neural Networks (QCNNs) for pattern recognition, Quantum Long Short-Term Memory (QLSTM) for sequential modeling, and Quantum Reinforcement Learning (QRL) for decision making and control. Advanced topics such as Quantum Architecture Search (QAS), Quantum Fast Weight Programmers (QFWP), and the Quantum-Train (QT) framework are presented to illustrate how classical and quantum models can dynamically co-design and reprogram one another. Furthermore, we discuss federated and distributed quantum learning, encoding complexity, and training challenges such as barren plateaus and hardware constraints. The article concludes with a forward-looking outlook on scalable QAI systems, autonomous quantum agents, and the long-term vision of self-programming, distributed intelligence. By bridging quantum theory, learning algorithms, and system architectures, this work aims to offer both foundational understanding and strategic insights for the next generation of hybrid quantum-classical intelligence.
Artificial intelligence (AI) technology leads to new insights into the manipulation of quantum systems in the Noisy Intermediate-Scale Quantum (NISQ) era. Classical agent-based artificial intelligence algorithms provide a framework for the design or control of quantum systems. Traditional reinforcement learning methods are designed for the Markov Decision Process (MDP) and, hence, have difficulty in dealing with partially observable or quantum observable decision processes. Due to the difficulty of building or inferring a model of a specified quantum system, a model-free-based control approach is more practical and feasible than its counterpart of a model-based approach. In this work, we apply a model-free deep recurrent Q-network (DRQN) reinforcement learning method for qubit-based quantum circuit architecture design problems. This paper is the first attempt to solve the quantum circuit design problem from the recurrent reinforcement learning algorithm, while using discrete policy. Simulation results suggest that our long short-term memory (LSTM)-based DRQN method is able to learn quantum circuits for entangled Bell–Greenberger–Horne–Zeilinger (Bell–GHZ) states. However, since we also observe unstable learning curves in experiments, suggesting that the DRQN could be a promising method for AI-based quantum circuit design application, more investigation on the stability issue would be required.
In recent years, advancements in brain science and neuroscience have significantly influenced the field of computer science, particularly in the domain of reinforcement learning (RL). Drawing insights from neurobiology and neuropsychology, researchers have leveraged these findings to develop novel mechanisms for understanding intelligent decision-making processes in the brain. Concurrently, the emergence of quantum computing has opened new frontiers in artificial intelligence, leading to the development of quantum machine learning (QML). This study introduces a novel model that integrates Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, inspired by the complex workings of the human brain. Specifically designed for reinforcement learning tasks in energy-efficient environments, our approach progresses through two distinct stages mirroring sensory and memory systems. In the initial stage, analogous to the brain’s hypothalamus, low-level information is extracted to emulate sensory data processing patterns. Subsequently, resembling the hippocampus, this information is processed at a higher level, capturing and memorizing correlated patterns. We conduct a comparative analysis of our model against existing quantum models such as Quantum Neural Networks and their classical counterparts, elucidating its unique contributions. Through empirical results, we aim to underscore the effectiveness of our approach in optimizing energy consumption in practical scenarios.