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:2505.06300

ARDNS-FN-Quantum: A Quantum-Enhanced Reinforcement Learning Framework with Cognitive-Inspired Adaptive Exploration for Dynamic Environments

Umberto Gonçalves de Sousa

Published May 12, 2025• 1 citation
arXivHTMLPDF

Abstract

Reinforcement learning (RL) has transformed sequential decisionmaking, yet traditional algorithms like Deep Q-Networks (DQNs) and Proximal Policy Optimization (PPO) often struggle with efficient exploration, stability, and adaptability in dynamic environments. This study presents ARDNS-FN-Quantum (Adaptive Reward-Driven Neural Simulator with Quantum enhancement), a novel framework that integrates a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, and adaptive exploration strategies modulated by reward variance and curiosity. Evaluated in a 10X10 grid-world over 20,000 episodes, ARDNS-FN-Quantum achieves a 99.5% success rate (versus 81.3% for DQN and 97.0% for PPO), a mean reward of 9.0528 across all episodes (versus 1.2941 for DQN and 7.6196 for PPO), and an average of 46.7 steps to goal (versus 135.9 for DQN and 62.5 for PPO). In the last 100 episodes, it records a mean reward of 9.1652 (versus 7.0916 for DQN and 9.0310 for PPO) and 37.2 steps to goal (versus 52.7 for DQN and 53.4 for PPO). Graphical analyses, including learning curves, steps-to-goal trends, reward variance, and reward distributions, demonstrate ARDNS-FN-Quantum's superior stability (reward variance 5.424 across all episodes versus 252.262 for DQN and 76.583 for PPO) and efficiency. By bridging quantum computing, cognitive science, and RL, ARDNS-FN-Quantum offers a scalable, human-like approach to adaptive learning in uncertain environments, with potential applications in robotics, autonomous systems, and decision-making under uncertainty.

DOI
10.36227/techrxiv.174702508.85583877/v1

Related papers

Q-ARDNS-Multi: A Multi-Agent Quantum Reinforcement Learning Framework with Meta-Cognitive Adaptation for Complex 3D Environments

Umberto Gonçalves de Sousa

This paper presents Q-ARDNS-Multi, an advanced multi-agent quantum reinforcement learning (QRL) framework that extends the ARDNS-FN-Quantum model, where Q-ARDNS-Multi stands for "Quantum Adaptive Reward-Driven Neural Simulator - Multi-Agent". It integrates quantum circuits with RY gates, meta-cognitive adaptation, and multi-agent coordination mechanisms for complex 3D environments. Q-ARDNS-Multi leverages a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, a shared memory module for agent cooperation, and adaptive exploration strategies modulated by reward variance and intrinsic motivation. Evaluated in a $10 \times 10 \times 3$ GridWorld environment with two agents over 5000 episodes, Q-ARDNS-Multi achieves success rates of 99.6\% and 99.5\% for Agents 0 and 1, respectively, outperforming Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Soft Actor-Critic (SAC) in terms of success rate, stability, navigation efficiency, and collision avoidance. The framework records mean rewards of $-304.2891 \pm 756.4636$ and $-295.7622 \pm 752.7103$, averaging 210 steps to goal, demonstrating its robustness in dynamic settings. Comprehensive analyses, including learning curves, reward distributions, statistical tests, and computational efficiency evaluations, highlight the contributions of quantum circuits and meta-cognitive adaptation. By bridging quantum computing, cognitive science, and multi-agent RL, Q-ARDNS-Multi offers a scalable, human-like approach for applications in robotics, autonomous navigation, and decision-making under uncertainty.

arXiv:2506.03205•Jun 2, 2025•0 citations

A Quantum-Enhanced Framework for Human-Like Reinforcement Learning: ARDNS-P-Quantum with Piagetian Stages

Umberto Gonçalves de Sousa

Traditional reinforcement learning (RL) models like Deep Q-Networks (DQNs) often lack human-like capabilities such as multi-timescale memory, adaptive plasticity, and cognitive developmental stages. We introduce ARDNS-P-Quantum, an enhanced version of the Adaptive Reward-Driven Neural Simulator with Piagetian Developmental Stages (ARDNS-P), integrating quantum computing to improve action selection. Using a 2-qubit quantum circuit with RY rotations and 16 shots, ARDNS-P-Quantum leverages a dual-memory system and Piaget's developmental stages to achieve superior performance in a 10×10 grid-world. Over 20,000 episodes, ARDNS-P Quantum attains a 99.2% goal-reaching success rate (vs. 91.9% for ARDNS-P and 84.5% for DQN), reduces steps to goal to 33.3 (vs. 149.2 for ARDNS-P and 72.1 for DQN), and increases mean rewards to 9.1169 (vs. 9.12 for ARDNS-P and 3.2207 for DQN) in the last 100 episodes. The quantum circuit design, with fewer shots and optimized depth, enhances exploration efficiency. This framework bridges RL, neuroscience, developmental psychology, and quantum computing, offering a scalable approach for human-like learning in dynamic environments.

•Apr 18, 2025•2 citations

Quantum-Inspired Reinforcement Learning for Edge-Driven Cyber-Physical Systems

Jagjit Singh Dhatterwal, Sandeep Kumar, Shilpa Choudhary

The integration of Quantum-Inspired Reinforcement Learning (QiRL) into Edge-Driven CyberPhysical Systems (CPS) presents a transformative approach to enhance real-time decision-making in distributed environments. While classical reinforcement learning (RL) struggles with scalability and computational complexity in edge-CPS, quantum-inspired Quantum-Inspired Reinforcement Learning for Edge-Driven Cyber-Physical Systems algorithms leverage superposition and entanglement principles to optimize policy exploration and convergence. This paper proposes a novel QiRL framework that combines quantum-inspired optimization with deep RL, enabling efficient resource allocation and adaptive control in latency-sensitive applications (e.g., smart grids, autonomous drones). We formalize the mathematical foundations of QiRL, design a hybrid neural-quantum architecture for edge deployment, and evaluate its performance under dynamic CPS constraints. Simulations on IoT-based case studies demonstrate $\mathbf{2 0}-\mathbf{3 5 \%}$ faster convergence and $\mathbf{1 5 \%}$ higher energy efficiency compared to classical Deep Q-Networks (DQN). Key challenges, such as quantum noise simulation and edge-hardware limitations, are discussed to guide future research. This work bridges quantum computing principles with edge intelligence, offering a scalable pathway for nextgeneration CPS.

International Conference on Mobile Networks and Wireless Communications (ICMNWC)•Dec 10, 2025•0 citations

Quantum-Inspired Algorithms for Reinforcement Learning

Jincheng Zhang

This paper investigates the application of quantum-inspired algorithms to the field of reinforcement learning (RL). Traditional RL methods often struggle with exploration challenges and can be computationally expensive, particularly in complex environments. We propose a novel RL algorithm that leverages concepts from quantum mechanics, specifically superposition and entanglement, to address these limitations. The core idea is to represent states, actions, and rewards using quantum-inspired representations, allowing the agent to explore the environment more efficiently and potentially converge to optimal policies faster. This work presents a detailed formulation of the algorithm, including the mathematical framework and key considerations for implementation. The potential benefits of this approach, including improved exploration and reduced computational complexity, are discussed. The algorithm is designed to iteratively refine its policy based on simulated quantum measurements, aiming to minimize the expected return. The exploration strategy is guided by the inherent probabilistic nature of quantum states, leading to a more diverse and potentially faster learning process. Further research is warranted to fully explore the capabilities and limitations of this approach across various RL benchmark problems.

•Sep 1, 2026•0 citations

Quantum-Inspired Reinforcement Learning for Quantum Control

Haixu Yu, Xudong Zhao, Chunlin Chen

Reinforcement learning (RL) is considered a powerful technology with the potential to revolutionize quantum control. However, the application effectiveness of traditional RL is often limited by some insurmountable experimental conditions. Thus, developing new RL algorithms that can efficiently manipulate the quantum system dynamics is a crucial task. Prior research has shown that incorporating quantum mechanical properties into RL can improve learning performance. In this article, we consider the quantum control problem where only the target state can be accurately identified and introduce a quantum-inspired RL (QiRL) method. In particular, we propose a quantum-inspired exploration strategy to replace a commonly used$\epsilon $-greedy strategy, as well as a quantum-inspired reward scheme to incentivize the learning agent. Numerical results on three quantum system control problems, i.e., one-qubit closed quantum system, two-level open quantum system, and many-qubit closed quantum system, verify the effectiveness of QiRL. Comparison results show that the proposed QiRL outperforms existing RL algorithms (deep Q-network and proximal policy optimization) in terms of stability and efficiency for solving quantum control problems.

IEEE Transactions on Control Systems Technology•Aug 14, 2024•11 citations

Adaptive Multi-Objective Reinforcement Learning with Classical and Variational Quantum Deep Q-Networks

Kamineni Pravalika, Greeshma Chanduri, Md Moinuddin Bhuiyan

This paper presents an adaptive multi-objective reinforcement learning (MORL) framework integrating classical Deep Q-Networks (DQN) and Variational Quantum Circuit DQN (VQC-DQN).A modified CartPole environment provides two reward signals combined through an adaptive weighting mechanism that updates every 10 episodes and converges in 14 of 15 runs; a corrected replay buffer rescalarizes stored transitions with the current weight instead of a stale one.Across five weight configurations, classical DQN achieves the highest whole-training balance reward, while a parameter-matched Tiny-Classical baseline (37 parameters) attains the best normalized hypervolume (0.412 vs. 0.376 for VQC-DQN and 0.262 for classical); VQC-DQN outperforms Tiny-Classical on raw balance in 3 of 5 weight settings.Retraining VQC-DQN for 200 episodes instead of 150 increases near-convergence balance by 32-163%.At 200 episodes, VQC-DQN has higher point-estimate near-convergence balance than classical DQN across the tested weight settings; however, this comparison is suggestive rather than statistically established because of unequal seed counts, a single 20-episode evaluation window, and unavailable per-seed variance for this metric.A qubit-count sweep under a matched gradient-step budget finds no evidence of barren plateaus within the tested 2-10 qubit range (gradient norm increases, not decreases, with qubit count), while a Deep Sea Treasure benchmark shows classical DQN fails under extreme weights whereas VQC-DQN consistently reaches a treasure but converges to the shallowest policy.These results suggest that classical-versus-quantum comparisons are budget-dependent rather than absolute, pending variance-controlled, multi-seed confirmation.

International Journal of Computer Applications•Oct 23, 2026•0 citations
Reinforcement learning (RL) has transformed sequential decisionmaking, yet traditional algorithms like Deep Q-Networks (DQNs) and Proximal Policy Optimization (PPO) often struggle with efficient exploration, stability, and adaptability in dynamic environments. This study presents ARDNS-FN-Quantum (Adaptive Reward-Driven Neural Simulator with Quantum enhancement), a novel framework that integrates a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, and adaptive exploration strategies modulated by reward variance and curiosity. Evaluated in a 10X10 grid-world over 20,000 episodes, ARDNS-FN-Quantum achieves a 99.5% success rate (versus 81.3% for DQN and 97.0% for PPO), a mean reward of 9.0528 across all episodes (versus 1.2941 for DQN and 7.6196 for PPO), and an average of 46.7 steps to goal (versus 135.9 for DQN and 62.5 for PPO). In the last 100 episodes, it records a mean reward of 9.1652 (versus 7.0916 for DQN and 9.0310 for PPO) and 37.2 steps to goal (versus 52.7 for DQN and 53.4 for PPO). Graphical analyses, including learning curves, steps-to-goal trends, reward variance, and reward distributions, demonstrate ARDNS-FN-Quantum's superior stability (reward variance 5.424 across all episodes versus 252.262 for DQN and 76.583 for PPO) and efficiency. By bridging quantum computing, cognitive science, and RL, ARDNS-FN-Quantum offers a scalable, human-like approach to adaptive learning in uncertain environments, with potential applications in robotics, autonomous systems, and decision-making under uncertainty.
This paper presents Q-ARDNS-Multi, an advanced multi-agent quantum reinforcement learning (QRL) framework that extends the ARDNS-FN-Quantum model, where Q-ARDNS-Multi stands for "Quantum Adaptive Reward-Driven Neural Simulator - Multi-Agent". It integrates quantum circuits with RY gates, meta-cognitive adaptation, and multi-agent coordination mechanisms for complex 3D environments. Q-ARDNS-Multi leverages a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, a shared memory module for agent cooperation, and adaptive exploration strategies modulated by reward variance and intrinsic motivation. Evaluated in a 10×10×310 \times 10 \times 310×10×3 GridWorld environment with two agents over 5000 episodes, Q-ARDNS-Multi achieves success rates of 99.6\% and 99.5\% for Agents 0 and 1, respectively, outperforming Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Soft Actor-Critic (SAC) in terms of success rate, stability, navigation efficiency, and collision avoidance. The framework records mean rewards of −304.2891±756.4636-304.2891 \pm 756.4636−304.2891±756.4636 and −295.7622±752.7103-295.7622 \pm 752.7103−295.7622±752.7103, averaging 210 steps to goal, demonstrating its robustness in dynamic settings. Comprehensive analyses, including learning curves, reward distributions, statistical tests, and computational efficiency evaluations, highlight the contributions of quantum circuits and meta-cognitive adaptation. By bridging quantum computing, cognitive science, and multi-agent RL, Q-ARDNS-Multi offers a scalable, human-like approach for applications in robotics, autonomous navigation, and decision-making under uncertainty.
Traditional reinforcement learning (RL) models like Deep Q-Networks (DQNs) often lack human-like capabilities such as multi-timescale memory, adaptive plasticity, and cognitive developmental stages. We introduce ARDNS-P-Quantum, an enhanced version of the Adaptive Reward-Driven Neural Simulator with Piagetian Developmental Stages (ARDNS-P), integrating quantum computing to improve action selection. Using a 2-qubit quantum circuit with RY rotations and 16 shots, ARDNS-P-Quantum leverages a dual-memory system and Piaget's developmental stages to achieve superior performance in a 10×10 grid-world. Over 20,000 episodes, ARDNS-P Quantum attains a 99.2% goal-reaching success rate (vs. 91.9% for ARDNS-P and 84.5% for DQN), reduces steps to goal to 33.3 (vs. 149.2 for ARDNS-P and 72.1 for DQN), and increases mean rewards to 9.1169 (vs. 9.12 for ARDNS-P and 3.2207 for DQN) in the last 100 episodes. The quantum circuit design, with fewer shots and optimized depth, enhances exploration efficiency. This framework bridges RL, neuroscience, developmental psychology, and quantum computing, offering a scalable approach for human-like learning in dynamic environments.
The integration of Quantum-Inspired Reinforcement Learning (QiRL) into Edge-Driven CyberPhysical Systems (CPS) presents a transformative approach to enhance real-time decision-making in distributed environments. While classical reinforcement learning (RL) struggles with scalability and computational complexity in edge-CPS, quantum-inspired Quantum-Inspired Reinforcement Learning for Edge-Driven Cyber-Physical Systems algorithms leverage superposition and entanglement principles to optimize policy exploration and convergence. This paper proposes a novel QiRL framework that combines quantum-inspired optimization with deep RL, enabling efficient resource allocation and adaptive control in latency-sensitive applications (e.g., smart grids, autonomous drones). We formalize the mathematical foundations of QiRL, design a hybrid neural-quantum architecture for edge deployment, and evaluate its performance under dynamic CPS constraints. Simulations on IoT-based case studies demonstrate 20−35%\mathbf{2 0}-\mathbf{3 5 \%}20−35% faster convergence and 15%\mathbf{1 5 \%}15% higher energy efficiency compared to classical Deep Q-Networks (DQN). Key challenges, such as quantum noise simulation and edge-hardware limitations, are discussed to guide future research. This work bridges quantum computing principles with edge intelligence, offering a scalable pathway for nextgeneration CPS.
This paper investigates the application of quantum-inspired algorithms to the field of reinforcement learning (RL). Traditional RL methods often struggle with exploration challenges and can be computationally expensive, particularly in complex environments. We propose a novel RL algorithm that leverages concepts from quantum mechanics, specifically superposition and entanglement, to address these limitations. The core idea is to represent states, actions, and rewards using quantum-inspired representations, allowing the agent to explore the environment more efficiently and potentially converge to optimal policies faster. This work presents a detailed formulation of the algorithm, including the mathematical framework and key considerations for implementation. The potential benefits of this approach, including improved exploration and reduced computational complexity, are discussed. The algorithm is designed to iteratively refine its policy based on simulated quantum measurements, aiming to minimize the expected return. The exploration strategy is guided by the inherent probabilistic nature of quantum states, leading to a more diverse and potentially faster learning process. Further research is warranted to fully explore the capabilities and limitations of this approach across various RL benchmark problems.
Reinforcement learning (RL) is considered a powerful technology with the potential to revolutionize quantum control. However, the application effectiveness of traditional RL is often limited by some insurmountable experimental conditions. Thus, developing new RL algorithms that can efficiently manipulate the quantum system dynamics is a crucial task. Prior research has shown that incorporating quantum mechanical properties into RL can improve learning performance. In this article, we consider the quantum control problem where only the target state can be accurately identified and introduce a quantum-inspired RL (QiRL) method. In particular, we propose a quantum-inspired exploration strategy to replace a commonly used$\epsilon $-greedy strategy, as well as a quantum-inspired reward scheme to incentivize the learning agent. Numerical results on three quantum system control problems, i.e., one-qubit closed quantum system, two-level open quantum system, and many-qubit closed quantum system, verify the effectiveness of QiRL. Comparison results show that the proposed QiRL outperforms existing RL algorithms (deep Q-network and proximal policy optimization) in terms of stability and efficiency for solving quantum control problems.
This paper presents an adaptive multi-objective reinforcement learning (MORL) framework integrating classical Deep Q-Networks (DQN) and Variational Quantum Circuit DQN (VQC-DQN).A modified CartPole environment provides two reward signals combined through an adaptive weighting mechanism that updates every 10 episodes and converges in 14 of 15 runs; a corrected replay buffer rescalarizes stored transitions with the current weight instead of a stale one.Across five weight configurations, classical DQN achieves the highest whole-training balance reward, while a parameter-matched Tiny-Classical baseline (37 parameters) attains the best normalized hypervolume (0.412 vs. 0.376 for VQC-DQN and 0.262 for classical); VQC-DQN outperforms Tiny-Classical on raw balance in 3 of 5 weight settings.Retraining VQC-DQN for 200 episodes instead of 150 increases near-convergence balance by 32-163%.At 200 episodes, VQC-DQN has higher point-estimate near-convergence balance than classical DQN across the tested weight settings; however, this comparison is suggestive rather than statistically established because of unequal seed counts, a single 20-episode evaluation window, and unavailable per-seed variance for this metric.A qubit-count sweep under a matched gradient-step budget finds no evidence of barren plateaus within the tested 2-10 qubit range (gradient norm increases, not decreases, with qubit count), while a Deep Sea Treasure benchmark shows classical DQN fails under extreme weights whereas VQC-DQN consistently reaches a treasure but converges to the shallowest policy.These results suggest that classical-versus-quantum comparisons are budget-dependent rather than absolute, pending variance-controlled, multi-seed confirmation.