Graph-based Selection-Activation Reinforcement Learning for Heterogenous Multi-agent Collaboration

被引：0

作者：

Chen, Hao-Xiang ^{[1
,2
,3
]}

Zhang, Xi-Wen ^{[1
,2
]}

Shen, Jun-Nan ^{[3
]}

机构：

[1] Beijing Institute of Technology, Beijing,100081, China

[2] Beijing Institute of Technology, State Key Laboratory of Intelligent Control and Decision of Complex System, School of Automation, Beijing,100081, China

[3] Beijing Institute of Technology, Chongqing Innovation Center, Chongqing,401135, China

来源：

Chinese Control Conference, CCC | 2024年

关键词：

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Convolutional neural networks - Graph neural networks - Hierarchical systems - Matrix algebra - Network theory (graphs) - Reinforcement learning

引用

页码：5835 / 5840