Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network

doi:10.1109/TNNLS.2022.3215774

	Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network
	Du, Wei 1,2; Ding, Shifei 1,2; Zhang, Chenglong 1,2; Shi, Zhongzhi 3
	2022-11-04
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	10
摘要	Most recent research on multiagent reinforcement learning (MARL) has explored how to deploy cooperative policies for homogeneous agents. However, realistic multiagent environments may contain heterogeneous agents that have different attributes or tasks. The heterogeneity of the agents and the diversity of relationships cause the learning of policy excessively tough. To tackle this difficulty, we present a novel method that employs a heterogeneous graph attention network to model the relationships between heterogeneous agents. The proposed method can generate an integrated feature representation for each agent by hierarchically aggregating latent feature information of neighbor agents, with the importance of the agent level and the relationship level being entirely considered. The method is agnostic to specific MARL methods and can be flexibly integrated with diverse value decomposition methods. We conduct experiments in predator-prey and StarCraft Multiagent Challenge (SMAC) environments, and the empirical results demonstrate that the performance of our method is superior to existing methods in several heterogeneous scenarios.
关键词	Reinforcement learning Multi-agent systems Aggregates Task analysis Scalability Marine vehicles Learning systems Graph attention network heterogeneous agents multiagent reinforcement learning (MARL) relationship-level attention
DOI	10.1109/TNNLS.2022.3215774
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61976216] ; National Natural Science Foundation of China[62276265]
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:000881975400001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：15[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19856
专题	中国科学院计算技术研究所期刊论文
通讯作者	Ding, Shifei
作者单位	1.China Univ Min & Technol, Sch Comp Sci & Technol, Xuzhou 221116, Jiangsu, Peoples R China 2.China Univ Min & Technol, Minist Educ, Mine Digitizat Engn Res Ctr, Xuzhou 221116, Jiangsu, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Du, Wei,Ding, Shifei,Zhang, Chenglong,et al. Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:10.
APA	Du, Wei,Ding, Shifei,Zhang, Chenglong,&Shi, Zhongzhi.(2022).Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,10.
MLA	Du, Wei,et al."Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):10.