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

Computer Engineering and Applications Journal

Multi-Agent Q-learning based on quantum theory and ant colony algorithm

Wang Sheng-bin

Published Jan 1, 2010• 0 citations
OpenAlex

Abstract

Due to the interactions among the Agents in the cooperative multi-Agent systems,multi-Agent learning problem complexity can rise rapidly with the number of Agents or their behavioral sophistication.In order to converge to desirable equilibrium,Agents generally require sufficient exploration of strategy space and coordinate their policies to achieve optimal equilibrium.A novel cooperative multi-Agent learning method is proposed based on quantum theory,ant algorithm and Q-learning.First,this method not only coordinates Agents'behaviors using quantum entanglement and helps Agents make action selection under quantum superposition,but also adopts Grover's searching algorithm which can probe the action,speed up learn-ing.Second,according to ant algorithm,footmark thought is presented so that Agents can be indirectly enforced to communicate with others.At last,the theory analysis and result of experiment both demonstrate that the improved Q-learning is feasible and increases the learning efficiency.

Related papers

Cooperative multi-agent reinforcement learning based on quantum computing

Xiangping Meng

Due to the interactions among the agents in the cooperative multi-agent systems,multi-agent learning problem complexity can rise rapidly with the number of agents or their behavioral sophistication.In order to converge to desirable equilibrium,agents generally require sufficient exploration of strategy space and coordinate their policies to achieve optimal equilibrium.A novel cooperative multi-agent learning method is proposed based on quantum theory and reinforcement learning.This method not only coordinates agents’ behaviors using quantum entanglement and helps agents make action selection under quantum superposition,but also adopts Grover’s searching algorithm which can speed up learning.This method also makes a good tradeoff between exploration and exploitation using probability characteristics of quantum theory.The results of simulated experiments show that quantum theory can be effectively used to cooperative multi-agent reinforcement learning.

Computer Engineering and Applications Journal•Jan 1, 2008•0 citations

Quantum Ant Colony Algorithm for the Multi-task Coalition Problem

Chunnian Liu

With concentration on the defects of ant colony algorithm as not-high precision and much iteration existing in the algorithm of multi-task coalition problem(MTCP),this dissertation utilized the characteristics of quantum computation simultaneously processing substantial quanta in parallel to put forward quantum ant colony algorithm on MTCP.First,it utilized quantum superposition states to give quantum code based on Agent,making each Agent occupy 2 positions in the space;Second,in order for the rotation angle to obtain proper size and direction,it posed the self-adaptive and corrective rotation angle adjusting strategy on the basis of pheromone;Finally,it gave ant algorithm-seeking strategy based on the quantum states by monitoring on the quantum code.Substantial simulation experiments show that,compared with existing algorithms,this one can not only obtain better algorithm,but also improve the convergence speed prominently.

Journal of Beijing University of Technology•Jan 1, 2013•1 citation

Research on quantum satellite access selection based on Q-learning quantum ant colony algorithm

Yan Kang, Min Nie, Guang Yang

The development and deployment of low-orbit quantum satellites has become one of the important research directions in the field of quantum communication technology. In order to improve the security and service quality of quantum satellite network, this paper proposes a multi-attribute quantum satellite selection access technique based on Q-learning quantum ant colony. Considering the two optimization objectives of path combined trust value and path cost, the overall trust function is defined according to the direct trust value and indirect trust value to improve the security, and the cost function is defined according to the channel QBER(Quantum bit error rate), interstellar transmission delay, and channel establishment rate to improve the service quality. Simulation results show that compared with the traditional ant colony optimization algorithm and the improved quantum ant colony multi-constraint algorithm, the Q-learning quantum ant colony algorithm significantly improves the performance indexes such as the packet delivery rate and the system blocking rate of the quantum satellite access selection, and improves the convergence speed, which is of certain reference significance for the research on the access selection of quantum satellites.

•Sep 20, 2024•0 citations

Fidelity-Based Ant Colony Optimization for Control of Quantum System

Hang Zhang, Yifeng Tu, Ying Guo

The search time of traditional ant colony Algorithm (ACA) is too long, and it tends to trap in local optimizations. In this paper, a fidelity-based ACA with Q-learning is presented to solve above-mentioned problem and applied for control of quantum system. In the fidelity-based ACA with Q-learning, fidelity is used in heuristic function, which can help the system converge to the optimal solution. And the fidelity-based ACA with Q-learning can simplify the parameter setting of ACA algorithm. An example (a spin-1/2 system) is demonstrated to test the performance of the fidelity-based ACA with Q-learning. The results show that the fidelity-based ACA with Q-learning can efficiently avoid trapping in local optimal policies and increase the speed of convergence process.

International Conference on Smart Grid and Electrical Automation (ICSGEA)•May 1, 2017•1 citation

A Novel Quantum Ant Colony Optimizing Algorithm

Yang Jia, Xu Qiang, Jinrong Zhang +1 more

Aiming at the shortcoming of optimization problems in continuous space based on ant colony optimization which is easy to fall into local optimums and has a slow convergence rate,a novel quantum ant colony optimization algorithm is presented.In this algorithm,each ant position is represented by a group of quantum bits;a new quantum rotation gates are designed to update the position of the ant so as to enable the ant to move.Some quantum bits are mutated by quantum non-gate so as to increase the variety of ant positions.It not only proves the convergence of the proposed algorithms through theoretical analysis,but also demonstrates that the algorithm can double searching space,maintain better population diversity,rapider convergence speed and global optimal ability than the classical ant colony algorithm by simulation experiments.

Acta Scientiarum Naturalium Universitatis Sunyatseni•May 25, 2009•3 citations

QMARL: A Quantum Multi-Agent Reinforcement Learning Framework for Swarm Robots Navigation

Weizhao Chen, Jiawang Wan, Fangwen Ye +2 more

In the last decade, the field of reinforcement learning has evolved from single-agent paradigms to embrace multi-agent settings. However, as the number of agents increases, especially in intricate or stochastic environments, the efficacy of individual learning models tends to diminish. Moreover, applying experience replay techniques in multi-agent scenarios presents considerable challenges. To address these pressing issues, this paper introduces a straightforward yet highly effective approach known as Quantum-Based Multi-Agent Reinforcement Learning (QMARL). This approach revolves around the quantization of states and actions within the multi-agent reinforcement learning system. Leveraging the power of the Grover algorithm for action decision-making, we also introduce a novel quantum-based prioritized experience replay method. Our proposed approach has been rigorously validated through experiments conducted in the cooperative navigation environment provided by OpenAI. The results demonstrate its capacity to enhance multi-agent learning in complex settings. This research opens promising avenues for harnessing quantum computing techniques in the realm of reinforcement learning, paving the way for more robust and scalable solutions in multi-agent systems.

IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)•Apr 14, 2024•3 citations
Due to the interactions among the Agents in the cooperative multi-Agent systems,multi-Agent learning problem complexity can rise rapidly with the number of Agents or their behavioral sophistication.In order to converge to desirable equilibrium,Agents generally require sufficient exploration of strategy space and coordinate their policies to achieve optimal equilibrium.A novel cooperative multi-Agent learning method is proposed based on quantum theory,ant algorithm and Q-learning.First,this method not only coordinates Agents'behaviors using quantum entanglement and helps Agents make action selection under quantum superposition,but also adopts Grover's searching algorithm which can probe the action,speed up learn-ing.Second,according to ant algorithm,footmark thought is presented so that Agents can be indirectly enforced to communicate with others.At last,the theory analysis and result of experiment both demonstrate that the improved Q-learning is feasible and increases the learning efficiency.
Due to the interactions among the agents in the cooperative multi-agent systems,multi-agent learning problem complexity can rise rapidly with the number of agents or their behavioral sophistication.In order to converge to desirable equilibrium,agents generally require sufficient exploration of strategy space and coordinate their policies to achieve optimal equilibrium.A novel cooperative multi-agent learning method is proposed based on quantum theory and reinforcement learning.This method not only coordinates agents’ behaviors using quantum entanglement and helps agents make action selection under quantum superposition,but also adopts Grover’s searching algorithm which can speed up learning.This method also makes a good tradeoff between exploration and exploitation using probability characteristics of quantum theory.The results of simulated experiments show that quantum theory can be effectively used to cooperative multi-agent reinforcement learning.
With concentration on the defects of ant colony algorithm as not-high precision and much iteration existing in the algorithm of multi-task coalition problem(MTCP),this dissertation utilized the characteristics of quantum computation simultaneously processing substantial quanta in parallel to put forward quantum ant colony algorithm on MTCP.First,it utilized quantum superposition states to give quantum code based on Agent,making each Agent occupy 2 positions in the space;Second,in order for the rotation angle to obtain proper size and direction,it posed the self-adaptive and corrective rotation angle adjusting strategy on the basis of pheromone;Finally,it gave ant algorithm-seeking strategy based on the quantum states by monitoring on the quantum code.Substantial simulation experiments show that,compared with existing algorithms,this one can not only obtain better algorithm,but also improve the convergence speed prominently.
The development and deployment of low-orbit quantum satellites has become one of the important research directions in the field of quantum communication technology. In order to improve the security and service quality of quantum satellite network, this paper proposes a multi-attribute quantum satellite selection access technique based on Q-learning quantum ant colony. Considering the two optimization objectives of path combined trust value and path cost, the overall trust function is defined according to the direct trust value and indirect trust value to improve the security, and the cost function is defined according to the channel QBER(Quantum bit error rate), interstellar transmission delay, and channel establishment rate to improve the service quality. Simulation results show that compared with the traditional ant colony optimization algorithm and the improved quantum ant colony multi-constraint algorithm, the Q-learning quantum ant colony algorithm significantly improves the performance indexes such as the packet delivery rate and the system blocking rate of the quantum satellite access selection, and improves the convergence speed, which is of certain reference significance for the research on the access selection of quantum satellites.
The search time of traditional ant colony Algorithm (ACA) is too long, and it tends to trap in local optimizations. In this paper, a fidelity-based ACA with Q-learning is presented to solve above-mentioned problem and applied for control of quantum system. In the fidelity-based ACA with Q-learning, fidelity is used in heuristic function, which can help the system converge to the optimal solution. And the fidelity-based ACA with Q-learning can simplify the parameter setting of ACA algorithm. An example (a spin-1/2 system) is demonstrated to test the performance of the fidelity-based ACA with Q-learning. The results show that the fidelity-based ACA with Q-learning can efficiently avoid trapping in local optimal policies and increase the speed of convergence process.
Aiming at the shortcoming of optimization problems in continuous space based on ant colony optimization which is easy to fall into local optimums and has a slow convergence rate,a novel quantum ant colony optimization algorithm is presented.In this algorithm,each ant position is represented by a group of quantum bits;a new quantum rotation gates are designed to update the position of the ant so as to enable the ant to move.Some quantum bits are mutated by quantum non-gate so as to increase the variety of ant positions.It not only proves the convergence of the proposed algorithms through theoretical analysis,but also demonstrates that the algorithm can double searching space,maintain better population diversity,rapider convergence speed and global optimal ability than the classical ant colony algorithm by simulation experiments.
In the last decade, the field of reinforcement learning has evolved from single-agent paradigms to embrace multi-agent settings. However, as the number of agents increases, especially in intricate or stochastic environments, the efficacy of individual learning models tends to diminish. Moreover, applying experience replay techniques in multi-agent scenarios presents considerable challenges. To address these pressing issues, this paper introduces a straightforward yet highly effective approach known as Quantum-Based Multi-Agent Reinforcement Learning (QMARL). This approach revolves around the quantization of states and actions within the multi-agent reinforcement learning system. Leveraging the power of the Grover algorithm for action decision-making, we also introduce a novel quantum-based prioritized experience replay method. Our proposed approach has been rigorously validated through experiments conducted in the cooperative navigation environment provided by OpenAI. The results demonstrate its capacity to enhance multi-agent learning in complex settings. This research opens promising avenues for harnessing quantum computing techniques in the realm of reinforcement learning, paving the way for more robust and scalable solutions in multi-agent systems.