CASIA OpenIR  > 复杂系统认知与决策实验室  > 决策指挥与体系智能
SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning
Zhiwei Xu1,2; Yunpeng Bai1,2; Dapeng Li1,2; Bin Zhang1,2; Guoliang Fan1,2
2022
Conference NameInternational Conference on Autonomous Agents and Multi-Agent Systems(AAMAS)
Pages1400-1408
Conference DateMay 9-13, 2022
Conference PlaceAuckland, New Zealand
Abstract

As one of the solutions to the decentralized partially observable Markov decision process (Dec-POMDP) problems, the value decomposition method has achieved significant results recently. However, most value decomposition methods require the fully observable state of the environment during training, but this is not feasible in some scenarios where only incomplete and noisy observations can be obtained. Therefore, we propose a novel value decomposition framework, named State Inference for value DEcomposition (SIDE), which eliminates the need to know the global state by simultaneously seeking solutions to the two problems of optimal control and state inference. SIDE can be extended to any value decomposition method to tackle partially observable problems. By comparing with the performance of different algorithms in StarCraft II micromanagement tasks, we verified that though without accessible states, SIDE can infer the current state that contributes to the reinforcement learning process based on past local observations and even achieve superior results to many baselines in some complex scenarios.

DOI10.5555/3535850.3536006
URL查看原文
Indexed ByEI
Language英语
IS Representative Paper
Sub direction classification多智能体系统
planning direction of the national heavy laboratory多智能体决策
Paper associated data
Citation statistics
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56522
Collection复杂系统认知与决策实验室_决策指挥与体系智能
Corresponding AuthorGuoliang Fan
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
Zhiwei Xu,Yunpeng Bai,Dapeng Li,et al. SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning[C],2022:1400-1408.
Files in This Item: Download All
File Name/Size DocType Version Access License
SIDE State Inference(2965KB)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
[Zhiwei Xu]'s Articles
[Yunpeng Bai]'s Articles
[Dapeng Li]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhiwei Xu]'s Articles
[Yunpeng Bai]'s Articles
[Dapeng Li]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhiwei Xu]'s Articles
[Yunpeng Bai]'s Articles
[Dapeng Li]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: SIDE State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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