CASIA OpenIR  > 复杂系统认知与决策实验室  > 飞行器智能技术
Attention enhanced reinforcement learning for multi-agent cooperation
Zhiqiang Pu1; Huimu Wang2; Zhen Liu1; Jianqiang Yi1; Shiguang Wu1
Source PublicationIEEE Transactions on Neural Networks and Learning Systems
2022
Issue2022Pages:1-15
Abstract

In this article, a novel method, called attention enhanced reinforcement learning (AERL), is proposed to address issues including complex interaction, limited communication range, and time-varying communication topology for multi agent cooperation. AERL includes a communication enhanced network (CEN), a graph spatiotemporal long short-term memory network (GST-LSTM), and parameters sharing multi-pseudo critic proximal policy optimization (PS-MPC-PPO). Specifically, CEN based on graph attention mechanism is designed to enlarge the agents’ communication range and to deal with complex interaction among the agents. GST-LSTM, which replaces the standard fully connected (FC) operator in LSTM with graph attention operator, is designed to capture the temporal dependence while maintaining the spatial structure learned by CEN. PS-MPC-PPO, which extends proximal policy optimization (PPO) in multi agent systems with parameters’ sharing to scale to environments with a large number of agents in training, is designed with multi-pseudo critics to mitigate the bias problem in training and accelerate the convergence process. Simulation results for three groups of representative scenarios including formation control, group containment, and predator–prey games demonstrate the effectiveness and robustness of AERL.

KeywordAttention mechanism deep reinforcement learning (DRL) graph convolutional networks multi agent systems
DOI10.1109/TNNLS.2022.3146858
URL查看原文
Indexed BySCI
Language英语
Sub direction classification强化与进化学习
Citation statistics
Cited Times:9[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/47425
Collection复杂系统认知与决策实验室_飞行器智能技术
Corresponding AuthorHuimu Wang
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhiqiang Pu,Huimu Wang,Zhen Liu,et al. Attention enhanced reinforcement learning for multi-agent cooperation[J]. IEEE Transactions on Neural Networks and Learning Systems,2022(2022):1-15.
APA Zhiqiang Pu,Huimu Wang,Zhen Liu,Jianqiang Yi,&Shiguang Wu.(2022).Attention enhanced reinforcement learning for multi-agent cooperation.IEEE Transactions on Neural Networks and Learning Systems(2022),1-15.
MLA Zhiqiang Pu,et al."Attention enhanced reinforcement learning for multi-agent cooperation".IEEE Transactions on Neural Networks and Learning Systems .2022(2022):1-15.
Files in This Item:
File Name/Size DocType Version Access License
Final Pub. - Attenti(2967KB)期刊论文作者接受稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhiqiang Pu]'s Articles
[Huimu Wang]'s Articles
[Zhen Liu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhiqiang Pu]'s Articles
[Huimu Wang]'s Articles
[Zhen Liu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhiqiang Pu]'s Articles
[Huimu Wang]'s Articles
[Zhen Liu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Final Pub. - Attention_Enhanced_Reinforcement_Learning_for_Multi_agent_Cooperation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.