CASIA OpenIR  > 综合信息系统研究中心  > 飞行器智能技术
Multi-agent Collaborative Learning with Relational Graph Reasoning in Adversarial Environments
Wu Shiguang1,2; Qiu Tenghai1; Pu Zhiqiang1,2; Yi Jianqiang1,2
2021-09-27
Conference Name2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Conference Date2021-9
Conference Place线上会议
Abstract

This paper proposes a collaborative policy framework via relational graph reasoning for multi-agent systems to accomplish adversarial tasks. A relational graph reasoning module consisting of an agent graph reasoning module and an opponent graph module, is designed to enable each agent to learn mixture state representation to enhance the effectiveness of the policy. In particular, for each agent, the agent graph reasoning module is designed to infer different underlying influences from different opponents and generate agent-level state representation. The opponent graph reasoning module is creatively designed for the opponents to reason relations from their surrounding objects including the agents and the opponents based on their latent features and then predict the future state of the opponents. It forms an opponent-level state representation. Besides, in order to effectively predict the state of the opponents, an intrinsic reward based on prediction error is designed to motivate the policy learning. Furthermore, interactions among agents are utilized to transmit messages and fuse information to promote the cooperative behaviors among the agents. Finally, various representative simulations on two multi-agent adversarial tasks are conducted to demonstrate the superiority and effectiveness of the proposed framework by comparison with existing methods.

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48728
Collection综合信息系统研究中心_飞行器智能技术
Corresponding AuthorQiu Tenghai
Affiliation1.Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wu Shiguang,Qiu Tenghai,Pu Zhiqiang,et al. Multi-agent Collaborative Learning with Relational Graph Reasoning in Adversarial Environments[C],2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-agent_Collabor(1396KB)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
[Wu Shiguang]'s Articles
[Qiu Tenghai]'s Articles
[Pu Zhiqiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wu Shiguang]'s Articles
[Qiu Tenghai]'s Articles
[Pu Zhiqiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu Shiguang]'s Articles
[Qiu Tenghai]'s Articles
[Pu Zhiqiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-agent_Collaborative_Learning_with_Relational_Graph_Reasoning_in_Adversarial_Environments.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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