CASIA OpenIR  > 复杂系统认知与决策实验室  > 听觉模型与认知计算
Filtered Observations for Model-Based Multi-agent Reinforcement Learning
Meng Linghui1,2; Xiong Xuantang1,2; Zang Yifan1,2; Zhang Xi1; Li Guoqi1,2; Xing Dengpeng1,2; Xu Bo1,2
2023-09
Conference NameJoint European Conference on Machine Learning and Knowledge Discovery in Database, 2023
Conference Date2023.9.18-2023.9.22
Conference PlaceTurin, Italy
Abstract

Reinforcement learning (RL) pursues high sample efficiency in practical environments to avoid costly interactions. Learning to plan with a world model in a compact latent space for policy optimization significantly improves sample efficiency in single-agent RL. Although world model construction methods for single-agent can be naturally extended, existing multi-agent schemes fail to acquire world models effectively as redundant information increases rapidly with the number of agents. To address this issue, we in this paper leverage guided diffusion to filter this noisy information, which harms teamwork. Obtained purified global states are then used to build a unified world model. Based on the learned world model, we denoise each agent observation and plan for multi-agent policy optimization, facilitating efficient cooperation. We name our method UTOPIA, a model-based method for cooperative multi-agent reinforcement learning (MARL). Compared to strong model-free and model-based baselines, our method shows enhanced sample efficiency in various testbeds, including the challenging StarCraft Multi-Agent Challenge tasks.

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
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57332
Collection复杂系统认知与决策实验室_听觉模型与认知计算
Corresponding AuthorXing Dengpeng; Xu Bo
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
Meng Linghui,Xiong Xuantang,Zang Yifan,et al. Filtered Observations for Model-Based Multi-agent Reinforcement Learning[C],2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
utopia_full_paper.pd(841KB)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
[Meng Linghui]'s Articles
[Xiong Xuantang]'s Articles
[Zang Yifan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Meng Linghui]'s Articles
[Xiong Xuantang]'s Articles
[Zang Yifan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Meng Linghui]'s Articles
[Xiong Xuantang]'s Articles
[Zang Yifan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: utopia_full_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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