检索结果-南通市图书馆

multi-agent Dynamic Area Coverage Based on reinforcement learning with Connected agents

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第4期45卷 215-230页

作者： Fatih Aydemir Aydin Cetin STM Defence Technologies Engineering and Trade.Inc. Ankara06560Turkey Department of Computer Engineering Faculty of TechnologyGazi UniversityAnkara06500Turkey

Dynamic area coverage with small unmanned aerial vehicle(UAV)systems is one of the major research topics due to limited payloads and the difficulty of decentralized decision-making *** behavior of a group of UAVs in an unknown environment is another hard problem to be *** this paper,we propose a method for decentralized execution of multi-UAVs for dynamic area coverage *** proposed decentralized decision-making dynamic area coverage(DDMDAC)method utilizes reinforcement learning(RL)where each UAV is represented by an intelligent agent that learns policies to create collaborative behaviors in partially observable *** agents increase their global observations by gathering information about the environment by connecting with other *** connectivity provides a consensus for the decision-making process,while each agent takes *** each step,agents acquire all reachable agents’states,determine the optimum location for maximal area coverage and receive reward using the covered rate on the target area,*** method was tested in a multi-agent actor-critic simulation *** the study,it has been considered that each UAV has a certain communication distance as in real *** results show that UAVs with limited communication distance can act jointly in the target area and can successfully cover the area without guidance from the central command unit.

关键词： Dynamic environments multi-agent reinforcement learning dynamic area coverage

A Weighted Mean Field reinforcement learning Algorithm for Large-Scale multi-agent Collaboration

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Guidance, Navigation and Control 2023年第2期3卷 38-56页

作者： Xinwei Yuan He Wang Wenwu Yu Suzhou Joint Graduate School Southeast University SuzhouJiangsu Province 215123P.R.China School of Mathematics Southeast University NanjingJiangsu Province 210096P.R.China

reinforcement learning has been proven to be an effective approach for solving multi-agent coordination problems in a dynamic open *** dealing with multi-agent cooper-ation issues,the mean field multi-agent reinforcement leaming method can better overcome the problems of slow learning speed,unstable convergent performance,and poor learning ***,the original mean field algorithm cannot extract features well when agents *** order to solve the large-scale multi-agent coordination problem,in this paper,the mean field multi-agent reinforcement learning algorithm is improved and optimized by combining the multi-head attention mechanism,and the attention-based mean field(MFA)structure is *** employment of a multi-head attention mechanism can optimize the interaction among agents,extract more effective cluster features and enable agents to learn more efficient *** paper first introduces the framework structure of MFA and then expounds on the relevant theoretical basis based on the Q-learning and Actor-Critic algorithms,and finally conducts large-scale multi-agent cooperative experiments on the Magent *** ex-perimental results show that compared with the baseline algorithm,the attention-based mean field Q-learning(MFQA)and attention-based Actor-Critic(MFACA)algorithms can make large-scale multi-agent clusters converge to higher rewards,and perform better than the original mean field multi-agent algorithm.

关键词： multi-agent reinforcement learning large-scale collaboration optimization attention mechanism

维普期刊数据库

multi-agent Hierarchical Graph Attention reinforcement learning for Grid-Aware Energy Management

在线全文

学校读者我要写书评

暂无评论

ZTE Communications 2023年第3期21卷 11-21页

作者： FENG Bingyi FENG Mingxiao WANG Minrui ZHOU Wengang LI Houqiang University of Science and Technology of China Hefei 230026China

The increasing adoption of renewable energy has posed challenges for voltage regulation in power distribution *** energy management,which includes the control of smart inverters and energy management systems,is a trending way to mitigate this ***,existing multi-agent reinforcement learning methods for grid-aware energy management have not sufficiently considered the importance of agent cooperation and the unique characteristics of the grid,which leads to limited *** this study,we propose a new approach named multi-agent hierarchical graph attention reinforcement learning framework(MAHGA)to stabilize the ***,under the paradigm of centralized training and decentralized execution,we model the power distribution network as a novel hierarchical graph containing the agent-level topology and the bus-level *** a hierarchical graph attention model is devised to capture the complex correlation between ***,we incorporate graph contrastive learning as an auxiliary task in the reinforcement learning process to improve representation learning from *** on several real-world scenarios reveal that our approach achieves the best performance and can reduce the number of voltage violations remarkably.

关键词： demand-side management graph neural networks multi-agent reinforcement learning voltage regulation

维普期刊数据库

Underwater multi-agent Cooperative Formation Hunting Based on Deep reinforcement learning

在线全文

学校读者我要写书评

暂无评论

Underwater Multi-agent Cooperative Formation Hunting Based o...

multi-agent Robust Time Differential reinforcement learning over communicated networks

第43届中国控制会议

作者： Xiaobo Shi Meiqin Liu Shanling Dong Ronghao Zheng Ping Wei College of Electrical Engineering Zhejiang University

In addressing the issue of formation hunting and trajectory planning for multi-autonomous underwater vehicles(AUVs) in complex underwater environments, traditional virtual structure algorithms, and leader-follower models exhibit shortcomings in environmental adaptability and vulnerability to single-point failures. To solve this problem, this article establishes a multi-agent reinforcement learning model with continuous state and action spaces, aiming to optimize the success rate and completion time of the formation hunting task. Furthermore, in establishing the simulation environment for underwater multi-AUVs, a reward function module for the formation hunting task is meticulously designed, taking into account various factors including navigation, formation, efficiency, boundary, and collision avoidance. The efficacy of the proposed methodology was substantiated through a comparative analysis involving the artificial potential field method and the proposed deep reinforcement learning algorithm within the simulation environment. Besides, the efficiency of task execution has improved by approximately 10%, with a success rate approaching 100%.

关键词： multi-agent reinforcement learning multi-AUVs formation hunting trajectory planning collision avoidance

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Multi-agent Robust Time Differential Reinforcement Learning ...

Policy evaluation for reinforcement learning over asynchronous multi-agent networks

第37届中国控制会议

作者： Jiahong Li Nan Ma Xiangmin Han School of Robotics Beijing Union University

Recently, the researches on multi-agent reinforcement learning（MARL） have attracted tremendous interest in many applications, especially for autonomous driving. The main problem of MARL is how to deal with the uncertainty in the environment and the interaction between the connected agents. To solve the problem, a distributed robust temporal differential deep Q-network algorithm（MARTD-DQN） was developed in this paper. MARTD-DQN consists of two parts, the decentralized MARL algorithm（DMARL） and the robust TD deep Q-network algorithm（RTD-DQN）. DMARL improves the robustness of the policy estimation by fusing the states from the neighbors over communicated networks. RTD-DQN improves the robustness to outliers through on-line estimation of the uncertainty. By combining the two algorithms, the proposed algorithm can be robust not only to node failures but also to the outliers. Then the proposed algorithm is applied to ACC simulations of autonomous *** simulation results are given to show the efficiency of the proposed algorithm.

关键词： multi-agent reinforcement learning MDPs Parameters Uncertainty Distributed Robust Estimation interactive cognition

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Policy evaluation for reinforcement learning over asynchrono...

An Overview of Intelligent Wireless Communications Using Deep reinforcement learning

第40届中国控制会议

作者： Xingyu Sha Jiaqi Zhang Keyou You Department of Automation and BNRist Tsinghua University

This paper proposes a fully asynchronous algorithm for policy evaluation of multi-agent reinforcement learning over networks. Without any form of coordination, agents can communicate with neighbors and compute their local variables using（possibly） delayed information at any time. Thus, the proposed scheme fully takes advantage of the distributed setting. We prove that our method converges to a neighborhood of the optimum at a linear rate, showing the computational advantage by reducing the amount of synchronization. Numerical experiments show that our method is robust to straggler agents.

关键词： multi-agent reinforcement learning multi-agent networks fully asynchronous updates policy evaluation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Communications and Information Networks 2019年第2期4卷 15-29页

作者： Yongming Huang Chunmei Xu Cheng Zhang Meng Hua Zhengming Zhang School of Information Science and Engineering Southeast UniversityNanjing 210096China Purple Mountain Laboratories Nanjing 211111China

Future wireless communication networks tend to be intelligentized to accomplish the missions that cannot be *** the new intelligent communication systems,optimizing the network perfor-mance has become a challenge due to the ever-increasing complexity of the network *** theories and technologies for intelligent wireless communications have obtained widespread attention,among which deep reinforcement learning(DRL)is an excellent machine learning *** has great potential in enhancing the intelligence of wireless communication systems while overcoming the above *** paper presents a review on applications of DRL in intelligent wireless com-munications with focuses on millimeter wave(mmWave),intelligent caching and unmanned aerial vehicle(UAV)*** first introduce the concepts and basic prin-ciples of single/multi-agent DRL ***,we review the related works where DRL algorithms are used to address emerging issues in wireless *** issues include mmWave communication,intelligent caching,UAV aided communication,and handover/access control in ***,critical challenges and future research directions of applying DRL in intelligent wireless communications are outlined.

关键词： deep reinforcement learning multi-agent reinforcement learning intelligent wireless communications mmWave caching UAV

Intelligent logistics system of steel bar warehouse based on ubiquitous information

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2021年第8期28卷 1367-1377页

作者： Hai-nan He Xiao-chen Wang Gong-zhuang Peng Dong Xu Yang Liu Min Jiang Ze-dong Wu Da Zhang He Yan National Engineering Research Center for Advanced Rolling Technology University of Science and Technology BeijingBeijing 100083China

Internet of Things and artificial intelligence technology are the key elements of the intelligent construction of iron and steel production warehouse. This paper puts forward a whole set of intelligent scheme for bar warehouse crane for the guidance of metallurgical process engineering, including cluster rapid self-awareness technology of the smart crane, precise self-executing technique of crane with rigid-flexible hybrid structure, multi-body system kinematics model of the smart crane sling and the swing characteristics model at different azimuth, antiswing control technology based on the optimization objective function, the vehicle model recognition system based on lidar, and the clustering crane dynamic scheduling method based on multi-agent reinforcement learning. The complete intelligent logistics system of the bar warehouse has changed the original operation mode of the warehouse area and realized the unmanned operation and intelligent scheduling of the crane,which is of great significance for improving the production efficiency, reducing the production cost, and improving the product quality.

关键词： intelligent warehouse crane vehicle identification anti-pendulum control multi-agent reinforcement learning

维普期刊数据库

On the complexity of computing Markov perfect equilibrium in general-sum stochastic games

在线全文

学校读者我要写书评

暂无评论

National Science Review 2023年第1期10卷 288-301页

作者： Xiaotie Deng Ningyuan Li David Mguni Jun Wang Yaodong Yang Center on Frontiers of Computing Studies School of Computer Science Peking University Center for multi-agent Research Institute for AI Peking University Huawei UK Computer Science University College London

Similar to the role of Markov decision processes in reinforcement learning,Markov games(also called stochastic games) lay down the foundation for the study of multi-agent reinforcement learning and se quential agent *** introduce approximate Markov perfect equilibrium as a solution to the computational problem of finite-state sto chastic games repeated in the infinite horizon and prove its *** solution concept preserves the Markov perfect property and opens up the possibility for the success of multi-agent reinforcement learning algorithms on static two-player games to be extended to multi-agent dynamic games,expanding the reign of the PPAD-complete class.

关键词： Markov game multi-agent reinforcement learning Markov perfect equilibrium PPAD-completeness stochastic game