CASIA OpenIR  > 智能系统与工程
Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning
Yang GK(杨光开)1,2; Chenhao(陈皓)1,2; Junge Zhang(张俊格)1,2; Qiyue Yin(尹奇跃)1,2; Kaiqi Huang(黄凯奇)1,2,3
2022-02
Conference NameInternational Joint Conference on Neural Networks
Conference Date2022-07
Conference Place意大利
Abstract

Cooperative multi-agent reinforcement learning has been considered promising to complete many complex cooperative tasks in the real world such as coordination of robot swarms and self-driving. To promote multi-agent cooperation, Centralized Training with Decentralized Execution emerges as a popular learning paradigm due to partial observability and communication constraints during execution and computational complexity in training. Value decomposition has been known to produce competitive performance to other methods in complex environment within this paradigm such as VDN and QMIX, which approximates the global joint Q-value function with multiple local individual Q-value functions. However, existing works often neglect the uncertainty of multiple agents resulting from the partial observability and very large action space in the multi-agent setting and can only obtain the sub-optimal policy. To alleviate the limitations above, building upon the value decomposition, we propose a novel method called multiagent uncertainty sharing (MAUS). This method utilizes the Bayesian neural network to explicitly capture the uncertainty
of all agents and combines with Thompson sampling to select actions for policy learning. Besides, we impose the uncertaintysharing mechanism among agents to stabilize training as well as coordinate the behaviors of all the agents for multi-agent cooperation. Extensive experiments on the StarCraft Multi-Agent
Challenge (SMAC) environment demonstrate that our approach achieves significant performance to exceed the prior baselines and verify the effectiveness of our method. 

Indexed ByEI
Funding ProjectNational Natural Science Foundation of China[61876181] ; National Natural Science Foundation of China[61876181]
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48977
Collection智能系统与工程
智能感知与计算
Corresponding AuthorJunge Zhang(张俊格)
Affiliation1.中科院自动化所
2.中国科学院大学人工智能学院
3.中国科学院脑科学与智能技术卓越创新中心
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yang GK,Chenhao,Junge Zhang,et al. Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-Agent Uncertai(2924KB)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
[Yang GK(杨光开)]'s Articles
[Chenhao(陈皓)]'s Articles
[Junge Zhang(张俊格)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang GK(杨光开)]'s Articles
[Chenhao(陈皓)]'s Articles
[Junge Zhang(张俊格)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang GK(杨光开)]'s Articles
[Chenhao(陈皓)]'s Articles
[Junge Zhang(张俊格)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning Camera Ready.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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