Knowledge Commons of Institute of Automation,CAS
NVIF: Neighboring Variational Information Flow for Cooperative Large-Scale Multiagent Reinforcement Learning | |
Chai, Jiajun1,2![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
![]() |
ISSN | 2162-237X |
2023-09-06 | |
页码 | 13 |
摘要 | Communication-based multiagent reinforcement learning (MARL) has shown promising results in promoting cooperation by enabling agents to exchange information. However, the existing methods have limitations in large-scale multiagent systems due to high information redundancy, and they tend to overlook the unstable training process caused by the online-trained communication protocol. In this work, we propose a novel method called neighboring variational information flow (NVIF), which enhances communication among neighboring agents by providing them with the maximum information set (MIS) containing more information than the existing methods. NVIF compresses the MIS into a compact latent state while adopting neighboring communication. To stabilize the overall training process, we introduce a two-stage training mechanism. We first pretrain the NVIF module using a randomly sampled offline dataset to create a task-agnostic and stable communication protocol, and then use the pretrained protocol to perform online policy training with RL algorithms. Our theoretical analysis indicates that NVIF-proximal policy optimization (PPO), which combines NVIF with PPO, has the potential to promote cooperation with agent-specific rewards. Experiment results demonstrate the superiority of our method in both heterogeneous and homogeneous settings. Additional experiment results also demonstrate the potential of our method for multitask learning. |
关键词 | Large-scale multiagent neighboring communication reinforcement learning (RL) variational information flow |
DOI | 10.1109/TNNLS.2023.3309608 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Strategic Priority Research Program of Chinese Academy of Sciences (CAS)[XDA27030400] ; National Natural Science Foundation of China[62293541] ; National Natural Science Foundation of China[62136008] ; National Key Research and Development Program of China[2018AAA0102404] ; Youth Innovation Promotion Association of CAS |
项目资助者 | Strategic Priority Research Program of Chinese Academy of Sciences (CAS) ; National Natural Science Foundation of China ; National Key Research and Development Program of China ; Youth Innovation Promotion Association of CAS |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:001064555400001 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 强化与进化学习 |
国重实验室规划方向分类 | 多智能体决策 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/53195 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhu, Yuanheng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Chai, Jiajun,Zhu, Yuanheng,Zhao, Dongbin. NVIF: Neighboring Variational Information Flow for Cooperative Large-Scale Multiagent Reinforcement Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:13. |
APA | Chai, Jiajun,Zhu, Yuanheng,&Zhao, Dongbin.(2023).NVIF: Neighboring Variational Information Flow for Cooperative Large-Scale Multiagent Reinforcement Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13. |
MLA | Chai, Jiajun,et al."NVIF: Neighboring Variational Information Flow for Cooperative Large-Scale Multiagent Reinforcement Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):13. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
NVIF_Neighboring_Var(2469KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论