CASIA OpenIR  > 复杂系统认知与决策实验室  > 飞行器智能技术
Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems
Qingxu Fu1,2; Tenghai Qiu1; Jianqiang Yi1,2; Zhiqiang Pu1,2; Shiguang Wu1,2
2022
Conference NameThe Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)
Conference Date2022
Conference Placeonline
Abstract

When dealing with a series of imminent issues, humans can naturally concentrate on a subset of these concerning issues by prioritizing them according to their contributions to motivational indices, e.g., the probability of winning a game. This idea of concentration offers insights into reinforcement learning of sophisticated Large-scale Multi-Agent
Systems (LMAS) participated by hundreds of agents. In such an LMAS, each agent receives a long series of entity observations at each step, which can overwhelm existing aggregation networks such as graph attention networks and cause inefficiency. In this paper, we propose a concentration network called ConcNet. First, ConcNet scores the observed entities considering several motivational indices, e.g., expected survival time and state value of the agents, and then ranks, prunes, and aggregates the encodings of observed entities to extract features. Second, distinct from the well-known attention mechanism, ConcNet has a unique motivational subnetwork to explicitly consider the motivational indices when scoring the observed entities. Furthermore, we present a concentration policy gradient architecture that can learn effective policies in LMAS from scratch. Extensive experiments demonstrate that the presented architecture has excellent scalability and flexibility, and significantly outperforms existing methods on LMAS benchmarks.
 

Indexed ByEI
IS Representative Paper
Sub direction classification多智能体系统
planning direction of the national heavy laboratory无人集群自主系统对抗
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57209
Collection复杂系统认知与决策实验室_飞行器智能技术
Corresponding AuthorTenghai Qiu
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
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Qingxu Fu,Tenghai Qiu,Jianqiang Yi,et al. Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
2022 AAAI - Concentr(5807KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qingxu Fu]'s Articles
[Tenghai Qiu]'s Articles
[Jianqiang Yi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qingxu Fu]'s Articles
[Tenghai Qiu]'s Articles
[Jianqiang Yi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qingxu Fu]'s Articles
[Tenghai Qiu]'s Articles
[Jianqiang Yi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2022 AAAI - Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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