中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 深度强化学习
Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning

文献类型：期刊论文

作者Hu, Guangzheng1,2; Zhu, Yuanheng1,2; Zhao, Dongbin1,2; Zhao, Mengchen3; Hao, Jianye3
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2021-10-29
页码13
关键词Bandwidth Protocols Reinforcement learning Task analysis Optimization Communication networks Multi-agent systems Event trigger limited bandwidth multi-agent communication multi-agent reinforcement learning (MARL)
ISSN号2162-237X
DOI10.1109/TNNLS.2021.3121546
通讯作者Zhu, Yuanheng(yuanheng.zhu@ia.ac.cn)
英文摘要Communicating agents with each other in a distributed manner and behaving as a group are essential in multi-agent reinforcement learning. However, real-world multi-agent systems suffer from restrictions on limited bandwidth communication. If the bandwidth is fully occupied, some agents are not able to send messages promptly to others, causing decision delay and impairing cooperative effects. Recent related work has started to address the problem but still fails in maximally reducing the consumption of communication resources. In this article, we propose an event-triggered communication network (ETCNet) to enhance communication efficiency in multi-agent systems by communicating only when necessary. For different task requirements, two paradigms of the ETCNet framework, event-triggered sending network (ETSNet) and event-triggered receiving network (ETRNet), are proposed for learning efficient sending and receiving protocols, respectively. Leveraging the information theory, the limited bandwidth is translated to the penalty threshold of an event-triggered strategy, which determines whether an agent at each step participates in communication or not. Then, the design of the event-triggered strategy is formulated as a constrained Markov decision problem and reinforcement learning finds the feasible and optimal communication protocol that satisfies the limited bandwidth constraint. Experiments on typical multi-agent tasks demonstrate that ETCNet outperforms other methods in reducing bandwidth occupancy and still preserves the cooperative performance of multi-agent systems at the most.
WOS关键词IMPROVING COORDINATION
资助项目National Key Research and Development Program of China[2018AAA0102404] ; National Natural Science Foundation of China[62136008] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA27030400] ; Youth Innovation Promotion Association CAS
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000732283100001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences ; Youth Innovation Promotion Association CAS
源URL[http://ir.ia.ac.cn/handle/173211/46965]  
专题复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者Zhu, Yuanheng
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Huawei, Noahs Ark Lab, Beijing 100085, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Guangzheng,Zhu, Yuanheng,Zhao, Dongbin,et al. Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:13.
APA Hu, Guangzheng,Zhu, Yuanheng,Zhao, Dongbin,Zhao, Mengchen,&Hao, Jianye.(2021).Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA Hu, Guangzheng,et al."Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):13.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。