CASIA OpenIR  > 复杂系统认知与决策实验室  > 飞行器智能技术
Learning Heterogeneous Agent Cooperation via Multiagent League Training
Qingxu, Fu1,2; Xiaolin Ai1,2; Jianqiang Yi1,2; Tenghai Qiu1,2; Wanmai Yuan1,2; Zhiqiang Pu1,2
Source PublicationIFAC World Congress
2023
PagesIFAC PapersOnLine 56-2 (2023) 3033-3040
Abstract

Many multiagent systems in the real world include multiple types of agents with different abilities and functionality. Such heterogeneous multiagent systems have significant practical advantages. However, they also come with challenges compared with homogeneous systems for multiagent reinforcement learning, such as the non-stationary problem and the policy version iteration issue. This work proposes a general-purpose reinforcement learning algorithm named Heterogeneous League Training (HLT) to address heterogeneous multiagent problems. HLT keeps track of a pool of policies that agents have explored during training, gathering a league of heterogeneous policies to facilitate future policy optimization. Moreover, a hyper-network is introduced to increase the diversity of agent behaviors when collaborating with teammates having different levels of cooperation skills. We use heterogeneous benchmark tasks to demonstrate that (1) HLT promotes the success rate in cooperative heterogeneous tasks; (2) HLT is an effective approach to solving the policy version iteration problem; (3) HLT provides a practical way to assess the difficulty of learning each role in a heterogeneous team.

Indexed ByEI
Language英语
Sub direction classification决策智能理论与方法
planning direction of the national heavy laboratory多智能体决策
Paper associated data
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57220
Collection复杂系统认知与决策实验室_飞行器智能技术
Affiliation1.中国科学院自动化研究所
2.中国科学院大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Qingxu, Fu,Xiaolin Ai,Jianqiang Yi,et al. Learning Heterogeneous Agent Cooperation via Multiagent League Training[J]. IFAC World Congress,2023:IFAC PapersOnLine 56-2 (2023) 3033-3040.
APA Qingxu, Fu,Xiaolin Ai,Jianqiang Yi,Tenghai Qiu,Wanmai Yuan,&Zhiqiang Pu.(2023).Learning Heterogeneous Agent Cooperation via Multiagent League Training.IFAC World Congress,IFAC PapersOnLine 56-2 (2023) 3033-3040.
MLA Qingxu, Fu,et al."Learning Heterogeneous Agent Cooperation via Multiagent League Training".IFAC World Congress (2023):IFAC PapersOnLine 56-2 (2023) 3033-3040.
Files in This Item: Download All
File Name/Size DocType Version Access License
Learning Heterogeneo(996KB)期刊论文作者接受稿开放获取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
[Xiaolin Ai]'s Articles
[Jianqiang Yi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qingxu, Fu]'s Articles
[Xiaolin Ai]'s Articles
[Jianqiang Yi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qingxu, Fu]'s Articles
[Xiaolin Ai]'s Articles
[Jianqiang Yi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Learning Heterogeneous Agent Cooperation via Multiagent League Training.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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