首页|期刊导航|无人系统（英文）|An Efficient Multi-Agent Policy Self-Play Learning Method Aiming at Seize-Control Scenarios

An Efficient Multi-Agent Policy Self-Play Learning Method Aiming at Seize-Control Scenarios

Huaqing Zhang Hongbin Ma Xiaofei Zhang Li Wang Minglei Han Hui Chen Ao Ding

无人系统（英文）2025，Vol.13Issue(4)：987-1004,18.

无人系统（英文）2025，Vol.13Issue(4)：987-1004,18.DOI:10.1142/S230138502550061X

An Efficient Multi-Agent Policy Self-Play Learning Method Aiming at Seize-Control Scenarios

Huaqing Zhang ¹Hongbin Ma ¹Xiaofei Zhang ²Li Wang ³Minglei Han ¹Hui Chen ¹Ao Ding¹

作者信息

1. School of Automation,Beijing Institute of Technology,Beijing 100081,P.R.China
2. School of Vehicle and Mobility,Tsinghua University,Beijing 100084,P.R.China
3. School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081,P.R.China
折叠

摘要

关键词

Self-play/cooperative confrontation/deep reinforcement learning/policy evaluation/wargame

Key words

Self-play/cooperative confrontation/deep reinforcement learning/policy evaluation/wargame

引用本文复制引用

Huaqing Zhang,Hongbin Ma,Xiaofei Zhang,Li Wang,Minglei Han,Hui Chen,Ao Ding..An Efficient Multi-Agent Policy Self-Play Learning Method Aiming at Seize-Control Scenarios[J].无人系统（英文）,2025,13(4):987-1004,18.

基金项目

This work was partially funded by the National Key Re-search and Development Plan of China(No.2018AAA0101000)and the National Natural Science Foundation of China under grant 62076028.This work is also funded by Innovation Fund of Qiyuan Lab. （No.2018AAA0101000）

无人系统（英文）

访问量0

下载量0

段落导航