Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

2022, Volume 23, Issue 7

Abstract

Keywords

Related Research

Back to Top

Frontiers of Information Technology & Electronic Engineering >> 2022, Volume 23, Issue 7 doi: 10.1631/FITEE.2100597

Cooperative planning of multi-agent systems based on task-oriented knowledge fusion with graph neural networks

Affiliation(s): Department of Automation, Tsinghua University, Beijing 100084, China; Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China; Office of Science and Technology, Tianjin University, Tianjin 300350, China; School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen 518107, China; Faculty Office of Electrical and Electronics Engineering, University of Nottingham, Ningbo 315154, China; less

Received: 2021-12-31 Accepted: 2022-07-21 Available online: 2022-07-21
HTML99 PDF 68 Collect 0

Next Previous

Abstract

is one of the critical problems in the field of gaming. This work focuses on when each agent has only a local observation range and local communication. We propose a novel architecture that combines a graph neural network with a sampling method. Two main contributions of this paper are based on the comparisons with previous work: (1) we realize feasible and dynamic adjacent information fusion using (i.e., Graph SAmple and aggreGatE), which is the first time this method has been used to deal with the problem, and (2) a task-oriented sampling method is proposed to aggregate the available knowledge from a particular orientation, to obtain an effective and stable training process in our model. Experimental results demonstrate the good performance of our proposed method.

Related Research