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:2407.20739 · Lecture notes in computer science

Architectural Influence on Variational Quantum Circuits in Multi-Agent Reinforcement Learning: Evolutionary Strategies for Optimization

Michael Kölle, Karola Schneider, Sabrina Egger, Felix Topp, Thomy Phan, Philipp J. Altmann, Jonas Nüßlein, Claudia Linnhoff–Popien

Published Jan 1, 2025• 1 citation
arXivHTMLPDF
DOI
10.1007/978-3-031-87327-0_3

Related papers

Quantum Reinforcement Learning: Analysis of the Influence of the Pqc Architecture, Q-Values and Observables on Agent Learning and Performance

Bernardo Manuel Pirozzo, Mariano De Paula, Sebastian Aldo Villar +1 more

•Jan 1, 2023•0 citations

Multi-Agent Quantum Reinforcement Learning Using Evolutionary Optimization

Michael Kölle, Felix Topp, Thomy Phan +3 more

Multi-Agent Reinforcement Learning is becoming increasingly more important in times of autonomous driving and other smart industrial applications. Simultaneously a promising new approach to Reinforcement Learning arises using the inherent properties of quantum mechanics, reducing the trainable parameters of a model significantly. However, gradient-based Multi-Agent Quantum Reinforcement Learning methods often have to struggle with barren plateaus, holding them back from matching the performance of classical approaches. While gradient free Quantum Reinforcement Learning methods may alleviate some of these challenges, they too are not immune to the difficulties posed by barren plateaus. We build upon an existing approach for gradient free Quantum Reinforcement Learning and propose three genetic variations with Variational Quantum Circuits for Multi-Agent Reinforcement Learning using evolutionary optimization. We evaluate our genetic variations in the Coin Game environment and also compare them to classical approaches. We showed that our Variational Quantum Circuit approaches perform significantly better compared to a neural network with a similar amount of trainable parameters. Compared to the larger neural network, our approaches archive similar results using $97.88\%$ less parameters.

arXiv:2311.05546•International Conference on Agents and Artificial Intelligence (ICAART)•Jan 1, 2024•6 citations

Quantum Reinforcement Learning with Adaptive Variational Quantum Circuits

Sarvesh Bendre, Samiksha Apake, Ashish Mishra +2 more

•Jan 1, 2025•0 citations

Multiagent reinforcement learning for efficient variational fast-forwarding quantum circuits

Fanxu Meng, Zhiguo Huang, Yuan Long +4 more

Physical Review A•Dec 24, 2025•0 citations

COMA++: Quantum-Enhanced Communication in Multi-Agent Reinforcement Learning for Marine Debris Collection Optimization

Can Savcı, Tansel Akgül, Berkant Bıçakçı

This paper presents a COMA++ hybrid quantum-classical multi-agent reinforcement learning framework for optimizing marine debris collection operations. The system combines GRU-based temporal modeling, multi-head attention mechanisms, and quantum-enhanced communication using dedicated variational quantum circuits. Multispectral Sentinel-2 satellite data and CNN-based semantic segmentation enable accurate marine waste detection. The core architecture features GRU-based 4-qubit Actors for handling partial observability, attention-based 6-qubit Critics for scalable coordination, and 3-qubit quantum communication circuits for emergent coordination protocols. Action masking prevents invalid movements while the enhanced COMA algorithm with counterfactual baselines optimizes multi-agent coordination. This quantum-enhanced communication system enables agents to develop non-classical coordination strategies impossible with traditional methods, demonstrating significant potential for complex environmental optimization tasks.

•Sep 17, 2025•1 citation

Variational quantum reinforcement learning via evolutionary optimization

Samuel Yen-Chi Chen, Chih-Min Huang, Chia-Wei Hsing +2 more

Abstract Recent advances in classical reinforcement learning (RL) and quantum computation point to a promising direction for performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in modern quantum devices. Here, we present two frameworks for deep quantum RL tasks using gradient-free evolutionary optimization. First, we apply the amplitude encoding scheme to the Cart-Pole problem, where we demonstrate the quantum advantage of parameter saving using amplitude encoding. Second, we propose a hybrid framework where the quantum RL agents are equipped with a hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs of dimensions exceeding the number of qubits. This allows us to perform quantum RL in the MiniGrid environment with 147-dimensional inputs. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.

arXiv:2109.00540•Machine Learning Science and Technology•Dec 21, 2021•108 citations
Multi-Agent Reinforcement Learning is becoming increasingly more important in times of autonomous driving and other smart industrial applications. Simultaneously a promising new approach to Reinforcement Learning arises using the inherent properties of quantum mechanics, reducing the trainable parameters of a model significantly. However, gradient-based Multi-Agent Quantum Reinforcement Learning methods often have to struggle with barren plateaus, holding them back from matching the performance of classical approaches. While gradient free Quantum Reinforcement Learning methods may alleviate some of these challenges, they too are not immune to the difficulties posed by barren plateaus. We build upon an existing approach for gradient free Quantum Reinforcement Learning and propose three genetic variations with Variational Quantum Circuits for Multi-Agent Reinforcement Learning using evolutionary optimization. We evaluate our genetic variations in the Coin Game environment and also compare them to classical approaches. We showed that our Variational Quantum Circuit approaches perform significantly better compared to a neural network with a similar amount of trainable parameters. Compared to the larger neural network, our approaches archive similar results using 97.88%97.88\%97.88% less parameters.
This paper presents a COMA++ hybrid quantum-classical multi-agent reinforcement learning framework for optimizing marine debris collection operations. The system combines GRU-based temporal modeling, multi-head attention mechanisms, and quantum-enhanced communication using dedicated variational quantum circuits. Multispectral Sentinel-2 satellite data and CNN-based semantic segmentation enable accurate marine waste detection. The core architecture features GRU-based 4-qubit Actors for handling partial observability, attention-based 6-qubit Critics for scalable coordination, and 3-qubit quantum communication circuits for emergent coordination protocols. Action masking prevents invalid movements while the enhanced COMA algorithm with counterfactual baselines optimizes multi-agent coordination. This quantum-enhanced communication system enables agents to develop non-classical coordination strategies impossible with traditional methods, demonstrating significant potential for complex environmental optimization tasks.
Abstract Recent advances in classical reinforcement learning (RL) and quantum computation point to a promising direction for performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in modern quantum devices. Here, we present two frameworks for deep quantum RL tasks using gradient-free evolutionary optimization. First, we apply the amplitude encoding scheme to the Cart-Pole problem, where we demonstrate the quantum advantage of parameter saving using amplitude encoding. Second, we propose a hybrid framework where the quantum RL agents are equipped with a hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs of dimensions exceeding the number of qubits. This allows us to perform quantum RL in the MiniGrid environment with 147-dimensional inputs. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.