智能科学与技术学报2024，Vol.6Issue(3)：301-318,18.DOI:10.11959/j.issn.2096-6652.202432
面向低轨星座边缘计算的博弈强化学习方法综述
Overview on game reinforcement learning methods for edge computing of low-orbit constellation
摘要
Abstract
As a new paradigm in the field of artificial intelligence,game reinforcement learning is an advanced mainstream method to solve the edge computing problem of low-orbit constellation.The multi-agent deep reinforcement learning inte-grated into the game perspective provides a new idea for dynamic,complex and uncertain constellation edge computing problems.By summarizing the three main research directions of satellite edge computing,namely satellite networking,task unloading and resource scheduling,the basis of game reinforcement learning paradigm is elaborated,and the typi-cal applications in the three research directions are described respectively from the methods of game model,deep Q network,deep deterministic strategy gradient and near-end strategy optimization.In the end,the paper looks forward to the frontier challenges in this field,expected to provide a reference for the cross-fusion research of game reinforce-ment learning paradigm and low-orbit constellation edge computing.关键词
低轨星座/边缘计算/博弈论/多智能体强化学习Key words
low-orbit constellation/edge computing/game theory/multi-agent reinforcement learning分类
信息技术与安全科学引用本文复制引用
谷学强,张万鹏,谭思雨,罗俊仁,周棪忠..面向低轨星座边缘计算的博弈强化学习方法综述[J].智能科学与技术学报,2024,6(3):301-318,18.基金项目
国家自然科学基金项目(No.92271108,No.62173336) The National Natural Science Foundation of China(No.92271108,No.62173336) （No.92271108,No.62173336）
