Knowledge Commons of Institute of Automation,CAS
Learning Robust Communication by Adversarial Training in Networked System Control | |
Runji, Lin1,2![]() | |
发表期刊 | Lecture Notes in Electrical Engineering
![]() |
2024-06 | |
页码 | Chapter 52 978-981-97-3335-4 |
摘要 | Effective communication is paramount to achieving efficient cooperation in networked system control (NSC). Nonetheless, real-world challenges such as node failures and channel noise impede the generalization capabilities of networked agents. In this study, we seek to enhance the robustness of networked control strategies by introducing RoComm. An adaptive adversary is incorporated during the training phase to emulate potential node failures. This adversary strategically targets and attacks vulnerable nodes in the system, prompting protagonist agents to adapt and become less susceptible to node failures over time. When both policies reach convergence, it indicates that the protagonist policy can sustain robust performance, even amidst the most detrimental noise. Empirical results from two distinct NSC scenarios—traffic signal control and adaptive cruise control—demonstrate that RoComm not only augments the resilience of networked control policies against node failures but also amplifies their generalization capacities across varying environmental conditions, subsequently elevating their overall performance. |
关键词 | Networked System Control Robustness Communicative Multi-Agent Reinforcement Learning |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 否 |
七大方向——子方向分类 | 决策智能理论与方法 |
国重实验室规划方向分类 | 认知决策知识体系 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57354 |
专题 | 复杂系统认知与决策实验室_群体决策智能团队 |
通讯作者 | Haifeng, Zhang |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences |
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 | Runji, Lin,Haifeng, Zhang. Learning Robust Communication by Adversarial Training in Networked System Control[J]. Lecture Notes in Electrical Engineering,2024:Chapter 52 978-981-97-3335-4. |
APA | Runji, Lin,&Haifeng, Zhang.(2024).Learning Robust Communication by Adversarial Training in Networked System Control.Lecture Notes in Electrical Engineering,Chapter 52 978-981-97-3335-4. |
MLA | Runji, Lin,et al."Learning Robust Communication by Adversarial Training in Networked System Control".Lecture Notes in Electrical Engineering (2024):Chapter 52 978-981-97-3335-4. |
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 | ||
论文原文-20230466-Learni(8334KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Runji, Lin]的文章 |
[Haifeng, Zhang]的文章 |
百度学术 |
百度学术中相似的文章 |
[Runji, Lin]的文章 |
[Haifeng, Zhang]的文章 |
必应学术 |
必应学术中相似的文章 |
[Runji, Lin]的文章 |
[Haifeng, Zhang]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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