In order to quickly and accurately locate the fault location of the distribution network and increase the stability of the distribution network,a fault recovery method based on multi-objective optimization algorithm i...In order to quickly and accurately locate the fault location of the distribution network and increase the stability of the distribution network,a fault recovery method based on multi-objective optimization algorithm is proposed.The optimization of the power distribution network fault system based on multiagent technology realizes fast recovery of multi-objective fault,solve the problem of network learning and parameter adjustment in the later stage of particle swarm optimization algorithm falling into the local extreme value dilemma,and realize the multi-dimensional nonlinear optimization of the main grid and the auxiliary grid.The system proposed in this study takes power distribution network as the goal,applies fuzzy probability algorithm,simplifies the calculation process,avoids local extreme value,and finally realizes the energy balance between each power grid.Simulation results show that the Multi-Agent Technology enjoys priority in restoring important load,shortening the recovery time of power grid balance,and reducing the overall line loss rate of power grid.Therefore,the power grid fault self-healing system can improve the safety and stability of the important power grid,and reduce the economic loss rate of the whole power grid.展开更多
Distributed Data Mining is expected to discover preciously unknown, implicit and valuable information from massive data set inherently distributed over a network. In recent years several approaches to distributed data...Distributed Data Mining is expected to discover preciously unknown, implicit and valuable information from massive data set inherently distributed over a network. In recent years several approaches to distributed data mining have been developed, but only a few of them make use of intelligent agents. This paper provides the reason for applying Multi-Agent Technology in Distributed Data Mining and presents a Distributed Data Mining System based on Multi-Agent Technology that deals with heterogeneity in such environment. Based on the advantages of both the CS model and agent-based model, the system is being able to address the specific concern of increasing scalability and enhancing performance.展开更多
Traditional ERP software system cannot efficiently su pport new management ideas such as BPR, DEM and virtual enterprise which emphasi zes that enterprise should be adjusted to market changes and business process ch a...Traditional ERP software system cannot efficiently su pport new management ideas such as BPR, DEM and virtual enterprise which emphasi zes that enterprise should be adjusted to market changes and business process ch ain and value chain should be integrated tightly. To solve these problems, this paper proposed the conception of Flexible ERP system. F-ERP is a self- adapti ve software system based on multi-agent technology. It developed the followin g kind of agents which are useful for F-ERP: business process agent, interf ace agent, data agent and decision and analysis agent. The F-ERP software syste m is an hierarchy system which is composed of data layer, system tools layer, bu siness application layer and business decision layer. It used component based de velopment mythology and complied with CORBA to development F-ERP. The F-ERP sy stem can support the new management ideas such as BPR, DEM and virtual enterpris e etc. By implementation of it, enterprise can improve its management and promot e its competence.展开更多
The genetic microarrays give to researchers a huge amount of data of many diseases represented by intensities of gene expression. In genomic medicine gene expression analysis is guided to find strategies for preventio...The genetic microarrays give to researchers a huge amount of data of many diseases represented by intensities of gene expression. In genomic medicine gene expression analysis is guided to find strategies for prevention and treatment of diseases with high rate of mortality like the different cancers. So, genomic medicine requires the use of complex information technology. The purpose of our paper is to present a multi-agent system developed in order to improve gene expression analysis with the automation of tasks about identification of genes involved in a cancer, and classification of tumors according to molecular biology. Agents that integrate the system, carry out reading files of intensity data of genes from microarrays, pre-processing of this information, and with machine learning methods make groups of genes involved in the process of a disease as well as the classification of samples that could propose new subtypes of tumors difficult to identify based on their morphology. Our results we prove that the multi-agent system requires a minimal intervention of user, and the agents generate knowledge that reduce the time and complexity of the work of prevention and diagnosis, and thus allow a more effective treatment of tumors.展开更多
The health monitoring for large-scale structures need to resolve a large number of difficulties,such as the data transmission and distributing information handling.To solve these problems,the technology of multi-agent...The health monitoring for large-scale structures need to resolve a large number of difficulties,such as the data transmission and distributing information handling.To solve these problems,the technology of multi-agent is a good candidate to be used in the field of structural health monitoring.A structural health monitoring system architecture based on multi-agent technology is proposed.The measurement system for aircraft airfoil is designed with FBG,strain gage,and corresponding signal processing circuit.The experiment to determine the location of the concentrate loading on the structure is carried on with the system combined with technologies of pattern recognition and multi-agent.The results show that the system can locate the concentrate loading of the aircraft airfoil at the accuracy of 91.2%.展开更多
Multi-agent reinforcement learning(MARL)has proven its effectiveness in cooperative multi-agent systems(MASs)but still faces issues on the curse of dimensionality and learning efficiency.The main difficulty is caused ...Multi-agent reinforcement learning(MARL)has proven its effectiveness in cooperative multi-agent systems(MASs)but still faces issues on the curse of dimensionality and learning efficiency.The main difficulty is caused by the strong inter-agent coupling nature embedded in an MARL problem,which is yet to be fully exploited in existing algorithms.In this work,we recognize a learning graph characterizing the dependence between individual rewards and individual policies.Then we propose a graph-based reward aggregation(GRA)method,which utilizes the inherent coupling relationship among agents to eliminate redundant information.Specifically,GRA passes information among cooperating agents through graph attention networks to obtain aggregated rewards that contribute to the fitting of the value function,making each agent learn a decentralized executable cooperation policy.In addition,we propose a variant of GRA,named GRA-decen,which achieves decentralized training and decentralized execution(DTDE)when each agent only has access to information of partial agents in the learning process.We conduct experiments in different environments and demonstrate the practicality and scalability of our algorithms.展开更多
This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination me...This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination methods that are solved by neural dynamics,the proposed strategy displays greater flexibility,adaptability and scalability.Furthermore,the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation.By introducing a dynamic error function,a fixed-time convergent zeroing neural network(FTCZNN)model is designed for the online solution of the AMAC strategy,with its convergence time upper bound derived theoretically.Finally,the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments.Numerical results indicate that this method can reduce the formation error to the order of 10^(-6)within 1.8 s.展开更多
This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to es...This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to estimate higher-order synchronization errors,enabling the controller to rely solely on relative output measurements.This approach significantly reduces the dependence on full-state information,which is often infeasible or costly in practical engineering applications.An output feedback control strategy is developed to overcome these limitations while ensuring robust and effective synchronization.Simulation results are provided to demonstrate the effectiveness of the proposed approach and validate the theoretical findings.展开更多
Multi-Agent Systems(MAS),which consist of multiple interacting agents,are crucial in Cyber-Physical Systems(CPS),because they improve system adaptability,efficiency,and robustness through parallel processing and colla...Multi-Agent Systems(MAS),which consist of multiple interacting agents,are crucial in Cyber-Physical Systems(CPS),because they improve system adaptability,efficiency,and robustness through parallel processing and collaboration.However,most existing unsupervised meta-learning methods are centralized and not suitable for multi-agent systems where data are distributed stored and inaccessible to all agents.Meta-GMVAE,based on Variational Autoencoder(VAE)and set-level variational inference,represents a sophisticated unsupervised meta-learning model that improves generative performance by efficiently learning data representations across various tasks,increasing adaptability and reducing sample requirements.Inspired by these advancements,we propose a novel Distributed Unsupervised Meta-Learning(DUML)framework based on Meta-GMVAE and a fusion strategy.Furthermore,we present a DUML algorithm based on Gaussian Mixture Model(DUMLGMM),where the parameters of the Gaussian-mixture are solved by an Expectation-Maximization algorithm.Simulations on Omniglot and Mini Image Net datasets show that DUMLGMM can achieve the performance of the corresponding centralized algorithm and outperform non-cooperative algorithm.展开更多
This paper focuses on the leader-following positive consensus problems of heterogeneous switched multi-agent systems.First,a state-feedback controller with dynamic compensation is introduced to achieve positive consen...This paper focuses on the leader-following positive consensus problems of heterogeneous switched multi-agent systems.First,a state-feedback controller with dynamic compensation is introduced to achieve positive consensus under average dwell time switching.Then sufficient conditions are derived to guarantee the positive consensus.The gain matrices of the control protocol are described using a matrix decomposition approach and the corresponding computational complexity is reduced by resorting to linear programming and co-positive Lyapunov functions.Finally,two numerical examples are provided to illustrate the results obtained.展开更多
In recent years,researchers have leveraged single-agent reinforcement learning to boost educational outcomes and deliver personalized interventions;yet this paradigm provides no capacity for inter-agent interaction.Mu...In recent years,researchers have leveraged single-agent reinforcement learning to boost educational outcomes and deliver personalized interventions;yet this paradigm provides no capacity for inter-agent interaction.Multi-agent reinforcement learning(MARL)overcomes this limitation by allowing several agents to learn simultaneously within a shared environment,each choosing actions that maximize its own or the group's rewards.By explicitly modeling and exploiting agent-to-agent dynamics,MARL can align those interactions with pedagogical goals such as peer tutoring,collaborative problem-solving,or gamified competition,thus opening richer avenues for adaptive and socially informed learning experiences.This survey investigates the impact of MARL on educational outcomes by examining evidence of its effectiveness in enhancing learner performance,engagement,equity,and reducing teacher workload compared to single agent or traditional approaches.It explores the educational domains and pedagogical problems addressed by MARL,identifies the algorithmic families used,and analyzes their influence on learning.The review also assesses experimental settings and evaluation metrics to determine ecological validity,and outlines current challenges and future research directions in applying MARL to education.展开更多
With the advent of sixth-generation mobile communications(6G),space-air-ground integrated networks have become mainstream.This paper focuses on collaborative scheduling for mobile edge computing(MEC)under a three-tier...With the advent of sixth-generation mobile communications(6G),space-air-ground integrated networks have become mainstream.This paper focuses on collaborative scheduling for mobile edge computing(MEC)under a three-tier heterogeneous architecture composed of mobile devices,unmanned aerial vehicles(UAVs),and macro base stations(BSs).This scenario typically faces fast channel fading,dynamic computational loads,and energy constraints,whereas classical queuing-theoretic or convex-optimization approaches struggle to yield robust solutions in highly dynamic settings.To address this issue,we formulate a multi-agent Markov decision process(MDP)for an air-ground-fused MEC system,unify link selection,bandwidth/power allocation,and task offloading into a continuous action space and propose a joint scheduling strategy that is based on an improved MATD3 algorithm.The improvements include Alternating Layer Normalization(ALN)in the actor to suppress gradient variance,Residual Orthogonalization(RO)in the critic to reduce the correlation between the twin Q-value estimates,and a dynamic-temperature reward to enable adaptive trade-offs during training.On a multi-user,dual-link simulation platform,we conduct ablation and baseline comparisons.The results reveal that the proposed method has better convergence and stability.Compared with MADDPG,TD3,and DSAC,our algorithm achieves more robust performance across key metrics.展开更多
To maximize the profits of power grid operators(GOs),load aggregators(LAs)and electricity customers(ECs),this paper proposes a hierarchical demand response(HDR)framework that considers competing interaction based on m...To maximize the profits of power grid operators(GOs),load aggregators(LAs)and electricity customers(ECs),this paper proposes a hierarchical demand response(HDR)framework that considers competing interaction based on multiagent deep deterministic policy gradient(MaDDPG).The ECs are divided into conventional ECs and the electric vehicles(EVs)which are managed by ECs agent(ECA)and EV agent(EVA)to exploit the flexibility of the HDR framework.Thus,the HDR is a tri-layer model determined by five types of agents engaging in competing interaction to maximize their own profits.To address the limitations of mathematical expression and participation scale in the Stackelberg game within the HDR model,a dynamic interaction mechanism is adopted.Moreover,to tackle the HDR involving various entities,the MaDDPG develops multiple agents to simulation the dynamic competing interactions between each subject as well as solve the problem of continuous action control.Furthermore,MaDDPG adopts soft target update and priority experience replay method to ensure stable and effective training,and makes the exploration strategy comprehensive by using exploration noise.Simulation studies are conducted to verify the performance of the MaDDPG with dynamic interaction mechanism in dealing with multilayer multi-agent continuous action control,compared to the double deep Q network(DDQN),deep Q network(DQN)and dueling DQN.Additionally,comparisons among the proposed HDR with the price based DR(PBDR)and incentive based DR(IBDR)are analyzed to investigate the flexibility of the HDR.展开更多
This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external di...This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external disturbances.Under the directed topology conditions,an observer-based finite-time control strategy based on adaptive backstepping and is proposed,in which a neural network-based state observer is employed to approximate the unmeasurable system state variables.To address the complexity explosion problem associated with the backstepping method,a finite-time command filter is incorporated,with error compensation signals designed to mitigate the filter-induced errors.Additionally,the Butterworth low-pass filter is introduced to avoid the algebraic ring problem in the design of the controller.The finite-time stability of the closed-loop system is rigorously analyzed with the finite-time Lyapunov stability criterion,validating that all closed-loop signals of the system remain bounded within a finite time.Finally,the effectiveness of the proposed control strategy is verified through a simulation example.展开更多
Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making p...Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making problems,significantly enhancing swarm intelligence in maneuvering.However,applying MARL to unmanned swarms presents two primary challenges.First,defensive agents must balance autonomy with collaboration under limited perception while coordinating against adversaries.Second,current algorithms aim to maximize global or individual rewards,making them sensitive to fluctuations in enemy strategies and environmental changes,especially when rewards are sparse.To tackle these issues,we propose an algorithm of MultiAgent Reinforcement Learning with Layered Autonomy and Collaboration(MARL-LAC)for collaborative confrontations.This algorithm integrates dual twin Critics to mitigate the high variance associated with policy gradients.Furthermore,MARL-LAC employs layered autonomy and collaboration to address multi-objective problems,specifically learning a global reward function for the swarm alongside local reward functions for individual defensive agents.Experimental results demonstrate that MARL-LAC enhances decision-making and collaborative behaviors among agents,outperforming the existing algorithms and emphasizing the importance of layered autonomy and collaboration in multi-agent systems.The observed adversarial behaviors demonstrate that agents using MARL-LAC effectively maintain cohesive formations that conceal their intentions by confusing the offensive agent while successfully encircling the target.展开更多
Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal ...Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.展开更多
With the accelerating aging process of China’s population,the demand for community elderly care services has shown diversified and personalized characteristics.However,problems such as insufficient total care service...With the accelerating aging process of China’s population,the demand for community elderly care services has shown diversified and personalized characteristics.However,problems such as insufficient total care service resources,uneven distribution,and prominent supply-demand contradictions have seriously affected service quality.Big data technology,with core advantages including data collection,analysis and mining,and accurate prediction,provides a new solution for the allocation of community elderly care service resources.This paper systematically studies the application value of big data technology in the allocation of community elderly care service resources from three aspects:resource allocation efficiency,service accuracy,and management intelligence.Combined with practical needs,it proposes optimal allocation strategies such as building a big data analysis platform and accurately grasping the elderly’s care needs,striving to provide operable path references for the construction of community elderly care service systems,promoting the early realization of the elderly care service goal of“adequate support and proper care for the elderly”,and boosting the high-quality development of China’s elderly care service industry.展开更多
This paper presents Dual Adaptive Neural Topology(Dual ANT),a distributed dual-network metaadaptive framework that enhances ant-colony-based multi-agent coordination with online introspection,adaptive parameter contro...This paper presents Dual Adaptive Neural Topology(Dual ANT),a distributed dual-network metaadaptive framework that enhances ant-colony-based multi-agent coordination with online introspection,adaptive parameter control,and privacy-preserving interactions.This approach improves standard Ant Colony Optimization(ACO)with two lightweight neural components:a forward network that estimates swarm efficiency in real time and an inverse network that converts these descriptors into parameter adaptations.To preserve the privacy of individual trajectories in shared pheromone maps,we introduce a locally differentially private pheromone update mechanism that adds calibrated noise to each agent’s pheromone deposit while preserving the efficacy of the global pheromone signal.The resulting systemenables agents to dynamically and autonomously adapt their coordination strategies under challenging and dynamic conditions,including varying obstacle layouts,uncertain target locations,and time-varying disturbances.Extensive simulations of large grid-based search tasks demonstrated that Dual ANT achieved faster convergence,higher robustness,and improved scalability compared to advanced baselines such asMulti-StrategyACO and Hierarchical ACO.The meta-adaptive feedback loop compensates for the performance degradation caused by privacy noise and prevents premature stagnation by triggering Levy flight exploration only when necessary.展开更多
In response to the Ministry of Education’s requirements for building distinctive model software schools,Software College of Northeastern University and Shenzhen Kingdom Technology Co.,Ltd.jointly developed the specia...In response to the Ministry of Education’s requirements for building distinctive model software schools,Software College of Northeastern University and Shenzhen Kingdom Technology Co.,Ltd.jointly developed the specialized course“Application and Practice of RPA Technology in FinTech”.Addressing pain points in financial digital transformation,the course integrates robotic process automation(RPA)principles,financial domain knowledge,and RPA platform practice into a“technology-scenario-capability”trinity teaching system.Through 64 credit hours of integrated theory and practice,it covers RPA fundamentals,financial applications,RPA operations(including core skills like Web/desktop automation),and AI integration,cultivating students’ability to design and implement automated financial workflows.It innovatively features a RPA simulation platform,30+financial case studies,and modular task resources,creating a“teacher-machine-student”interactive model.Practice demonstrates the course effectively enhances students’integration of technical application and business acumen,providing a scalable paradigm for cultivating interdisciplinary FinTech talent.展开更多
The moment a media delegation from the Republic of the Congo arrived at the Othello Kitchenware Museum on 18 November 2025,they were greeted with a vivid show of Guangdong’s industrial strength.Standing before them w...The moment a media delegation from the Republic of the Congo arrived at the Othello Kitchenware Museum on 18 November 2025,they were greeted with a vivid show of Guangdong’s industrial strength.Standing before them was not a typical exhibition hall,but a building shaped like a gleaming stainless-steel cooking pot.展开更多
基金This work is supported by the project of Hebei power technology of state grid from 2018 to 2019:Research and application of real-time situation assessment and visualization(SZKJXM20170445).
文摘In order to quickly and accurately locate the fault location of the distribution network and increase the stability of the distribution network,a fault recovery method based on multi-objective optimization algorithm is proposed.The optimization of the power distribution network fault system based on multiagent technology realizes fast recovery of multi-objective fault,solve the problem of network learning and parameter adjustment in the later stage of particle swarm optimization algorithm falling into the local extreme value dilemma,and realize the multi-dimensional nonlinear optimization of the main grid and the auxiliary grid.The system proposed in this study takes power distribution network as the goal,applies fuzzy probability algorithm,simplifies the calculation process,avoids local extreme value,and finally realizes the energy balance between each power grid.Simulation results show that the Multi-Agent Technology enjoys priority in restoring important load,shortening the recovery time of power grid balance,and reducing the overall line loss rate of power grid.Therefore,the power grid fault self-healing system can improve the safety and stability of the important power grid,and reduce the economic loss rate of the whole power grid.
文摘Distributed Data Mining is expected to discover preciously unknown, implicit and valuable information from massive data set inherently distributed over a network. In recent years several approaches to distributed data mining have been developed, but only a few of them make use of intelligent agents. This paper provides the reason for applying Multi-Agent Technology in Distributed Data Mining and presents a Distributed Data Mining System based on Multi-Agent Technology that deals with heterogeneity in such environment. Based on the advantages of both the CS model and agent-based model, the system is being able to address the specific concern of increasing scalability and enhancing performance.
文摘Traditional ERP software system cannot efficiently su pport new management ideas such as BPR, DEM and virtual enterprise which emphasi zes that enterprise should be adjusted to market changes and business process ch ain and value chain should be integrated tightly. To solve these problems, this paper proposed the conception of Flexible ERP system. F-ERP is a self- adapti ve software system based on multi-agent technology. It developed the followin g kind of agents which are useful for F-ERP: business process agent, interf ace agent, data agent and decision and analysis agent. The F-ERP software syste m is an hierarchy system which is composed of data layer, system tools layer, bu siness application layer and business decision layer. It used component based de velopment mythology and complied with CORBA to development F-ERP. The F-ERP sy stem can support the new management ideas such as BPR, DEM and virtual enterpris e etc. By implementation of it, enterprise can improve its management and promot e its competence.
文摘The genetic microarrays give to researchers a huge amount of data of many diseases represented by intensities of gene expression. In genomic medicine gene expression analysis is guided to find strategies for prevention and treatment of diseases with high rate of mortality like the different cancers. So, genomic medicine requires the use of complex information technology. The purpose of our paper is to present a multi-agent system developed in order to improve gene expression analysis with the automation of tasks about identification of genes involved in a cancer, and classification of tumors according to molecular biology. Agents that integrate the system, carry out reading files of intensity data of genes from microarrays, pre-processing of this information, and with machine learning methods make groups of genes involved in the process of a disease as well as the classification of samples that could propose new subtypes of tumors difficult to identify based on their morphology. Our results we prove that the multi-agent system requires a minimal intervention of user, and the agents generate knowledge that reduce the time and complexity of the work of prevention and diagnosis, and thus allow a more effective treatment of tumors.
基金supported by the Key Program of the National Science Foundation of China(50830201)Aviation Research Foundation(20060952)+1 种基金the National High Technology Research and Development of China(2007AA03Z117)the Natural Science Foundation of Jiansu Province(08kjd560009)
文摘The health monitoring for large-scale structures need to resolve a large number of difficulties,such as the data transmission and distributing information handling.To solve these problems,the technology of multi-agent is a good candidate to be used in the field of structural health monitoring.A structural health monitoring system architecture based on multi-agent technology is proposed.The measurement system for aircraft airfoil is designed with FBG,strain gage,and corresponding signal processing circuit.The experiment to determine the location of the concentrate loading on the structure is carried on with the system combined with technologies of pattern recognition and multi-agent.The results show that the system can locate the concentrate loading of the aircraft airfoil at the accuracy of 91.2%.
基金supported in part by the National Natural Science Foundation of China(grants 62203073 and 62573068)the Natural Science Foundation of Chongqing,China(grant CSTB2022NSCQMSX0577)。
文摘Multi-agent reinforcement learning(MARL)has proven its effectiveness in cooperative multi-agent systems(MASs)but still faces issues on the curse of dimensionality and learning efficiency.The main difficulty is caused by the strong inter-agent coupling nature embedded in an MARL problem,which is yet to be fully exploited in existing algorithms.In this work,we recognize a learning graph characterizing the dependence between individual rewards and individual policies.Then we propose a graph-based reward aggregation(GRA)method,which utilizes the inherent coupling relationship among agents to eliminate redundant information.Specifically,GRA passes information among cooperating agents through graph attention networks to obtain aggregated rewards that contribute to the fitting of the value function,making each agent learn a decentralized executable cooperation policy.In addition,we propose a variant of GRA,named GRA-decen,which achieves decentralized training and decentralized execution(DTDE)when each agent only has access to information of partial agents in the learning process.We conduct experiments in different environments and demonstrate the practicality and scalability of our algorithms.
基金supported by the National Natural Science Foundation of China under Grants 61962023,61562029 and 62466019.
文摘This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination methods that are solved by neural dynamics,the proposed strategy displays greater flexibility,adaptability and scalability.Furthermore,the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation.By introducing a dynamic error function,a fixed-time convergent zeroing neural network(FTCZNN)model is designed for the online solution of the AMAC strategy,with its convergence time upper bound derived theoretically.Finally,the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments.Numerical results indicate that this method can reduce the formation error to the order of 10^(-6)within 1.8 s.
文摘This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to estimate higher-order synchronization errors,enabling the controller to rely solely on relative output measurements.This approach significantly reduces the dependence on full-state information,which is often infeasible or costly in practical engineering applications.An output feedback control strategy is developed to overcome these limitations while ensuring robust and effective synchronization.Simulation results are provided to demonstrate the effectiveness of the proposed approach and validate the theoretical findings.
基金supported by the National Natural Science Foundation of China Youth Fund(No.62101579)。
文摘Multi-Agent Systems(MAS),which consist of multiple interacting agents,are crucial in Cyber-Physical Systems(CPS),because they improve system adaptability,efficiency,and robustness through parallel processing and collaboration.However,most existing unsupervised meta-learning methods are centralized and not suitable for multi-agent systems where data are distributed stored and inaccessible to all agents.Meta-GMVAE,based on Variational Autoencoder(VAE)and set-level variational inference,represents a sophisticated unsupervised meta-learning model that improves generative performance by efficiently learning data representations across various tasks,increasing adaptability and reducing sample requirements.Inspired by these advancements,we propose a novel Distributed Unsupervised Meta-Learning(DUML)framework based on Meta-GMVAE and a fusion strategy.Furthermore,we present a DUML algorithm based on Gaussian Mixture Model(DUMLGMM),where the parameters of the Gaussian-mixture are solved by an Expectation-Maximization algorithm.Simulations on Omniglot and Mini Image Net datasets show that DUMLGMM can achieve the performance of the corresponding centralized algorithm and outperform non-cooperative algorithm.
基金supported by the National Natural Science Foundation of China(62463007,62463005)the Natural Science Foundation of Hainan Province(625RC710,625MS047)+1 种基金the System Control and Information Processing Education Ministry Key Laboratory Open Funding,China(Scip20240119)the Science Research Funding of Hainan University,China(KYQD(ZR)22180,KYQD(ZR)23180).
文摘This paper focuses on the leader-following positive consensus problems of heterogeneous switched multi-agent systems.First,a state-feedback controller with dynamic compensation is introduced to achieve positive consensus under average dwell time switching.Then sufficient conditions are derived to guarantee the positive consensus.The gain matrices of the control protocol are described using a matrix decomposition approach and the corresponding computational complexity is reduced by resorting to linear programming and co-positive Lyapunov functions.Finally,two numerical examples are provided to illustrate the results obtained.
文摘In recent years,researchers have leveraged single-agent reinforcement learning to boost educational outcomes and deliver personalized interventions;yet this paradigm provides no capacity for inter-agent interaction.Multi-agent reinforcement learning(MARL)overcomes this limitation by allowing several agents to learn simultaneously within a shared environment,each choosing actions that maximize its own or the group's rewards.By explicitly modeling and exploiting agent-to-agent dynamics,MARL can align those interactions with pedagogical goals such as peer tutoring,collaborative problem-solving,or gamified competition,thus opening richer avenues for adaptive and socially informed learning experiences.This survey investigates the impact of MARL on educational outcomes by examining evidence of its effectiveness in enhancing learner performance,engagement,equity,and reducing teacher workload compared to single agent or traditional approaches.It explores the educational domains and pedagogical problems addressed by MARL,identifies the algorithmic families used,and analyzes their influence on learning.The review also assesses experimental settings and evaluation metrics to determine ecological validity,and outlines current challenges and future research directions in applying MARL to education.
文摘With the advent of sixth-generation mobile communications(6G),space-air-ground integrated networks have become mainstream.This paper focuses on collaborative scheduling for mobile edge computing(MEC)under a three-tier heterogeneous architecture composed of mobile devices,unmanned aerial vehicles(UAVs),and macro base stations(BSs).This scenario typically faces fast channel fading,dynamic computational loads,and energy constraints,whereas classical queuing-theoretic or convex-optimization approaches struggle to yield robust solutions in highly dynamic settings.To address this issue,we formulate a multi-agent Markov decision process(MDP)for an air-ground-fused MEC system,unify link selection,bandwidth/power allocation,and task offloading into a continuous action space and propose a joint scheduling strategy that is based on an improved MATD3 algorithm.The improvements include Alternating Layer Normalization(ALN)in the actor to suppress gradient variance,Residual Orthogonalization(RO)in the critic to reduce the correlation between the twin Q-value estimates,and a dynamic-temperature reward to enable adaptive trade-offs during training.On a multi-user,dual-link simulation platform,we conduct ablation and baseline comparisons.The results reveal that the proposed method has better convergence and stability.Compared with MADDPG,TD3,and DSAC,our algorithm achieves more robust performance across key metrics.
基金supported by the National Natural Science Foundation of China(No.52477097)the GuangDong Basic and Applied Basic Research Foundation(2023A1515240014)the State Key Laboratory of Advanced Electromagnetic Technology(Grant No.AET 2024KF005).
文摘To maximize the profits of power grid operators(GOs),load aggregators(LAs)and electricity customers(ECs),this paper proposes a hierarchical demand response(HDR)framework that considers competing interaction based on multiagent deep deterministic policy gradient(MaDDPG).The ECs are divided into conventional ECs and the electric vehicles(EVs)which are managed by ECs agent(ECA)and EV agent(EVA)to exploit the flexibility of the HDR framework.Thus,the HDR is a tri-layer model determined by five types of agents engaging in competing interaction to maximize their own profits.To address the limitations of mathematical expression and participation scale in the Stackelberg game within the HDR model,a dynamic interaction mechanism is adopted.Moreover,to tackle the HDR involving various entities,the MaDDPG develops multiple agents to simulation the dynamic competing interactions between each subject as well as solve the problem of continuous action control.Furthermore,MaDDPG adopts soft target update and priority experience replay method to ensure stable and effective training,and makes the exploration strategy comprehensive by using exploration noise.Simulation studies are conducted to verify the performance of the MaDDPG with dynamic interaction mechanism in dealing with multilayer multi-agent continuous action control,compared to the double deep Q network(DDQN),deep Q network(DQN)and dueling DQN.Additionally,comparisons among the proposed HDR with the price based DR(PBDR)and incentive based DR(IBDR)are analyzed to investigate the flexibility of the HDR.
基金supported in part by the Beijing Natural Science Foundation under Grant 4252050in part by the National Science Fund for Distinguished Young Scholars under Grant 62425304in part by the Basic Science Center Programs of NSFC under Grant 62088101.
文摘This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external disturbances.Under the directed topology conditions,an observer-based finite-time control strategy based on adaptive backstepping and is proposed,in which a neural network-based state observer is employed to approximate the unmeasurable system state variables.To address the complexity explosion problem associated with the backstepping method,a finite-time command filter is incorporated,with error compensation signals designed to mitigate the filter-induced errors.Additionally,the Butterworth low-pass filter is introduced to avoid the algebraic ring problem in the design of the controller.The finite-time stability of the closed-loop system is rigorously analyzed with the finite-time Lyapunov stability criterion,validating that all closed-loop signals of the system remain bounded within a finite time.Finally,the effectiveness of the proposed control strategy is verified through a simulation example.
基金co-supported by the National Natural Science Foundation of China(Nos.72371052 and 71871042).
文摘Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making problems,significantly enhancing swarm intelligence in maneuvering.However,applying MARL to unmanned swarms presents two primary challenges.First,defensive agents must balance autonomy with collaboration under limited perception while coordinating against adversaries.Second,current algorithms aim to maximize global or individual rewards,making them sensitive to fluctuations in enemy strategies and environmental changes,especially when rewards are sparse.To tackle these issues,we propose an algorithm of MultiAgent Reinforcement Learning with Layered Autonomy and Collaboration(MARL-LAC)for collaborative confrontations.This algorithm integrates dual twin Critics to mitigate the high variance associated with policy gradients.Furthermore,MARL-LAC employs layered autonomy and collaboration to address multi-objective problems,specifically learning a global reward function for the swarm alongside local reward functions for individual defensive agents.Experimental results demonstrate that MARL-LAC enhances decision-making and collaborative behaviors among agents,outperforming the existing algorithms and emphasizing the importance of layered autonomy and collaboration in multi-agent systems.The observed adversarial behaviors demonstrate that agents using MARL-LAC effectively maintain cohesive formations that conceal their intentions by confusing the offensive agent while successfully encircling the target.
文摘Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.
文摘With the accelerating aging process of China’s population,the demand for community elderly care services has shown diversified and personalized characteristics.However,problems such as insufficient total care service resources,uneven distribution,and prominent supply-demand contradictions have seriously affected service quality.Big data technology,with core advantages including data collection,analysis and mining,and accurate prediction,provides a new solution for the allocation of community elderly care service resources.This paper systematically studies the application value of big data technology in the allocation of community elderly care service resources from three aspects:resource allocation efficiency,service accuracy,and management intelligence.Combined with practical needs,it proposes optimal allocation strategies such as building a big data analysis platform and accurately grasping the elderly’s care needs,striving to provide operable path references for the construction of community elderly care service systems,promoting the early realization of the elderly care service goal of“adequate support and proper care for the elderly”,and boosting the high-quality development of China’s elderly care service industry.
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia,under project number NBU-FFR-2026-2441-02.
文摘This paper presents Dual Adaptive Neural Topology(Dual ANT),a distributed dual-network metaadaptive framework that enhances ant-colony-based multi-agent coordination with online introspection,adaptive parameter control,and privacy-preserving interactions.This approach improves standard Ant Colony Optimization(ACO)with two lightweight neural components:a forward network that estimates swarm efficiency in real time and an inverse network that converts these descriptors into parameter adaptations.To preserve the privacy of individual trajectories in shared pheromone maps,we introduce a locally differentially private pheromone update mechanism that adds calibrated noise to each agent’s pheromone deposit while preserving the efficacy of the global pheromone signal.The resulting systemenables agents to dynamically and autonomously adapt their coordination strategies under challenging and dynamic conditions,including varying obstacle layouts,uncertain target locations,and time-varying disturbances.Extensive simulations of large grid-based search tasks demonstrated that Dual ANT achieved faster convergence,higher robustness,and improved scalability compared to advanced baselines such asMulti-StrategyACO and Hierarchical ACO.The meta-adaptive feedback loop compensates for the performance degradation caused by privacy noise and prevents premature stagnation by triggering Levy flight exploration only when necessary.
文摘In response to the Ministry of Education’s requirements for building distinctive model software schools,Software College of Northeastern University and Shenzhen Kingdom Technology Co.,Ltd.jointly developed the specialized course“Application and Practice of RPA Technology in FinTech”.Addressing pain points in financial digital transformation,the course integrates robotic process automation(RPA)principles,financial domain knowledge,and RPA platform practice into a“technology-scenario-capability”trinity teaching system.Through 64 credit hours of integrated theory and practice,it covers RPA fundamentals,financial applications,RPA operations(including core skills like Web/desktop automation),and AI integration,cultivating students’ability to design and implement automated financial workflows.It innovatively features a RPA simulation platform,30+financial case studies,and modular task resources,creating a“teacher-machine-student”interactive model.Practice demonstrates the course effectively enhances students’integration of technical application and business acumen,providing a scalable paradigm for cultivating interdisciplinary FinTech talent.
文摘The moment a media delegation from the Republic of the Congo arrived at the Othello Kitchenware Museum on 18 November 2025,they were greeted with a vivid show of Guangdong’s industrial strength.Standing before them was not a typical exhibition hall,but a building shaped like a gleaming stainless-steel cooking pot.
