Knowledge Commons of Institute of Automation,CAS
Learning Cooperative Policies with Graph Networks in Distributed Swarm Systems | |
Zhang TL(张天乐)1,2![]() ![]() ![]() ![]() ![]() | |
2023 | |
会议名称 | IEEE International Joint Conference on Neural Networks |
会议日期 | June 18-23, 2023 |
会议地点 | Queensland, Australia |
出版者 | IEEE |
摘要 | Deriving efficient cooperative policies in uncertain dynamic environments poses huge challenges for a distributed swarm system due to the limited capability of the agents and the complex dynamics of the environment. In this paper, a novel distributed method based on deep reinforcement learning using observation-level and communication-level graph networks is proposed to learn cooperative policies for the distributed swarm system. Specifically, a relational directed graph attention neural network is designed to model observation-level graphs composed of heterogeneous relational graphs among each agent and each type of entities (e.g., obstacles, other teammates, opponents), for extracting different relational representations. Moreover, a relevant directed graph attention network is presented to cut off the ineffective communication among irrelevant agents, and model a relevant communication topology between each agent and relevant homogeneous neighbor agents as an communication-level graph, for promoting efficient inter-agent interactions. Furthermore, a distributed actor-critic algorithm with full parameter sharing is implemented to learn cooperative swarm policies by using distributed critics, which avoids the curse of dimensionality under a centralized critic. Various simulation results validate the effectiveness and generalization of the proposed method, and demonstrate that the proposed method outperforms existing state-of-the-art methods on coverage and pursuit tasks. |
收录类别 | EI |
语种 | 英语 |
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 | 多智能体决策 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51965 |
专题 | 复杂系统认知与决策实验室_飞行器智能技术 |
通讯作者 | Liu Z(刘振) |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学人工智能学院 3.中国电子科技集团 |
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 | Zhang TL,Liu Z,Pu ZQ,et al. Learning Cooperative Policies with Graph Networks in Distributed Swarm Systems[C]:IEEE,2023. |
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 | ||
2023-IJCNN.pdf(612KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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