VGN: Value Decomposition With Graph Attention Networks for Multiagent Reinforcement Learning
Wei, Qinglai1,2,3; Li, Yugu1; Zhang, Jie1; Wang, Fei-Yue1,3,4
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X
2022-05-18
页码14
通讯作者Zhang, Jie(jie.zhang@ia.ac.cn)
摘要Although value decomposition networks and the follow on value-based studies factorizes the joint reward function to individual reward functions for a kind of cooperative multiagent reinforcement problem, in which each agent has its local observation and shares a joint reward signal, most of the previous efforts, however, ignored the graphical information between agents. In this article, a new value decomposition with graph attention network (VGN) method is developed to solve the value functions by introducing the dynamical relationships between agents. It is pointed out that the decomposition factor of an agent in our approach can be influenced by the reward signals of all the related agents and two graphical neural network-based algorithms (VGN-Linear and VGN-Nonlinear) are designed to solve the value functions of each agent. It can be proved theoretically that the present methods satisfy the factorizable condition in the centralized training process. The performance of the present methods is evaluated on the StarCraft Multiagent Challenge (SMAC) benchmark. Experiment results show that our method outperforms the state-of-the-art value-based multiagent reinforcement algorithms, especially when the tasks are with very hard level and challenging for existing methods.
关键词Mathematical models Task analysis Games Q-learning Neural networks Behavioral sciences Training Deep learning graph attention networks (GATs) multiagent systems reinforcement learning
DOI10.1109/TNNLS.2022.3172572
收录类别SCI
语种英语
资助项目National Key Research and Development Program of China[2021YFE0206100] ; National Natural Science Foundation of China[62073321] ; National Defense Basic Scientific Research Program[JCKY2019203C029] ; Science and Technology Development Fund, Macau[0015/2020/AMJ]
项目资助者National Key Research and Development Program of China ; National Natural Science Foundation of China ; National Defense Basic Scientific Research Program ; Science and Technology Development Fund, Macau
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000798352100001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
被引频次:6[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/49411
专题多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队
多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者Zhang, Jie
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Macau Univ Sci & Technol, Inst Syst Engn, Macau 999078, Peoples R China
4.Qingdao Acad Intelligent Ind, Qingdao 266109, Peoples R China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Wei, Qinglai,Li, Yugu,Zhang, Jie,et al. VGN: Value Decomposition With Graph Attention Networks for Multiagent Reinforcement Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:14.
APA Wei, Qinglai,Li, Yugu,Zhang, Jie,&Wang, Fei-Yue.(2022).VGN: Value Decomposition With Graph Attention Networks for Multiagent Reinforcement Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,14.
MLA Wei, Qinglai,et al."VGN: Value Decomposition With Graph Attention Networks for Multiagent Reinforcement Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):14.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wei, Qinglai]的文章
[Li, Yugu]的文章
[Zhang, Jie]的文章
百度学术
百度学术中相似的文章
[Wei, Qinglai]的文章
[Li, Yugu]的文章
[Zhang, Jie]的文章
必应学术
必应学术中相似的文章
[Wei, Qinglai]的文章
[Li, Yugu]的文章
[Zhang, Jie]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。