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

Mathematics

Brain-Inspired Agents for Quantum Reinforcement Learning

Eva Andrés, Manuel Pegalájar Cuéllar, Gabriel Navarro

Published Apr 19, 2024• 8 citations
Publisher

Abstract

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.

DOI
10.3390/math12081230

Related papers

Brain-Inspired Quantum Neural Architectures for Pattern Recognition: Integrating QSNN and QLSTM

Eva Andrés, Manuel Pegalájar Cuéllar, Gabriel Navarro

Recent advances in the fields of deep learning and quantum computing have paved the way for innovative developments in artificial intelligence. In this manuscript, we leverage these cutting-edge technologies to introduce a novel model that emulates the intricate functioning of the human brain, designed specifically for the detection of anomalies such as fraud in credit card transactions. Leveraging the synergies of Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, our approach is developed in two distinct stages, closely mirroring the information processing mechanisms found in the brain's sensory and memory systems. In the initial stage, similar to the brain's hypothalamus, we extract low-level information from the data, emulating sensory data processing patterns. In the subsequent stage, resembling the hippocampus, we process this information at a higher level, capturing and memorizing correlated patterns. We will compare this model with other quantum models such as Quantum Neural Networks among others and their corresponding classical models.

arXiv:2505.01735•May 3, 2025•0 citations

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•Oct 26, 2022•1 citation

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.

IEEE International Conference on Acoustics Speech and Signal Processing•May 5, 2023•41 citations

Quantum-Inspired Reinforcement Learning Models for Adaptive Decision-Making in Neuromorphic Computational Systems

Pasuluri Binduswetha, Amjad Ali Syed, S. P. Maniraj +2 more

Recent progress in quantum-inspired computing and neuromorphic machine has rekindled the quest to develop learning systems capable of probabilistic thinking, and which can be run with the energy efficiency of the brain. However, the vast majority of reinforcement learning (RL) models can be described as being constrained by strict update policies and high power usage when implemented on a spiking architecture or an edge-based architecture. To fill this gap, it is proposed in this study that a Quantum-Inspired Reinforcement Learning (QiRL) framework can combine the policy encoding based on amplitude, and the neuromorphic adaptation to reach real-time and low-energy decision-making. In contrast to the traditional RL, QiRL incorporates phase-modulated dynamics of the interference to enhance positive learning and discourage reward oscillation.

Advances in computational intelligence and robotics book series•Mar 4, 2026•0 citations

Efficient Quantum Recurrent Reinforcement Learning Via Quantum Reservoir Computing

Samuel Yen-Chi Chen

Quantum reinforcement learning (QRL) has emerged as a framework to solve sequential decision-making tasks, showcasing empirical quantum advantages. A notable development is through quantum recurrent neural networks (QRNNs) for memory-intensive tasks such as partially observable environments. However, QRL models incorporating QRNN encounter challenges such as inefficient training of QRL with QRNN, given that the computation of gradients in QRNN is both computationally expensive and time-consuming. This work presents a novel approach to address this challenge by constructing QRL agents utilizing QRNN-based reservoirs, specifically employing quantum long short-term memory (QLSTM). QLSTM parameters are randomly initialized and fixed without training. The model is trained using the asynchronous advantage actor-critic (A3C) algorithm. Through numerical simulations, we validate the efficacy of our QLSTM-Reservoir RL framework. Its performance is assessed on standard benchmarks, demonstrating comparable results to a fully trained QLSTM RL model with identical architecture and training settings.

arXiv:2309.07339•IEEE International Conference on Acoustics Speech and Signal Processing•Mar 18, 2024•24 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
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.
Recent advances in the fields of deep learning and quantum computing have paved the way for innovative developments in artificial intelligence. In this manuscript, we leverage these cutting-edge technologies to introduce a novel model that emulates the intricate functioning of the human brain, designed specifically for the detection of anomalies such as fraud in credit card transactions. Leveraging the synergies of Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, our approach is developed in two distinct stages, closely mirroring the information processing mechanisms found in the brain's sensory and memory systems. In the initial stage, similar to the brain's hypothalamus, we extract low-level information from the data, emulating sensory data processing patterns. In the subsequent stage, resembling the hippocampus, we process this information at a higher level, capturing and memorizing correlated patterns. We will compare this model with other quantum models such as Quantum Neural Networks among others and their corresponding classical models.
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 QQQ-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.
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.
Recent progress in quantum-inspired computing and neuromorphic machine has rekindled the quest to develop learning systems capable of probabilistic thinking, and which can be run with the energy efficiency of the brain. However, the vast majority of reinforcement learning (RL) models can be described as being constrained by strict update policies and high power usage when implemented on a spiking architecture or an edge-based architecture. To fill this gap, it is proposed in this study that a Quantum-Inspired Reinforcement Learning (QiRL) framework can combine the policy encoding based on amplitude, and the neuromorphic adaptation to reach real-time and low-energy decision-making. In contrast to the traditional RL, QiRL incorporates phase-modulated dynamics of the interference to enhance positive learning and discourage reward oscillation.
Quantum reinforcement learning (QRL) has emerged as a framework to solve sequential decision-making tasks, showcasing empirical quantum advantages. A notable development is through quantum recurrent neural networks (QRNNs) for memory-intensive tasks such as partially observable environments. However, QRL models incorporating QRNN encounter challenges such as inefficient training of QRL with QRNN, given that the computation of gradients in QRNN is both computationally expensive and time-consuming. This work presents a novel approach to address this challenge by constructing QRL agents utilizing QRNN-based reservoirs, specifically employing quantum long short-term memory (QLSTM). QLSTM parameters are randomly initialized and fixed without training. The model is trained using the asynchronous advantage actor-critic (A3C) algorithm. Through numerical simulations, we validate the efficacy of our QLSTM-Reservoir RL framework. Its performance is assessed on standard benchmarks, demonstrating comparable results to a fully trained QLSTM RL model with identical architecture and training settings.
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.