Commander-Soldiers Reinforcement Learning for Cooperative Multi-Agent Systems | |
Chen YQ(陈逸群)1,2; Yang Wei1,2; Tianle Zhang1,2; Shiguang Wu1,2; Hongxing Chang2 | |
2022-07 | |
会议日期 | 2022-7 |
会议地点 | 意大利 |
英文摘要 | In ball sports, such as basketball, the coach can guide players to better offend and defend from a holistic perspective to win the game. Inspired by such scenarios, we introduce a coach-like concept into the decision-making process of cooperative multi-agent systems. We propose a new framework Commander-Soldiers Reinforcement Learning (CSRL), for Multi-Agent systems. Specifically, we introduce a virtual role, Commander, which can obtain and encode global information every T steps and send the encoded global guidance to Soldiers (real agents). Furthermore, we propose Policy Guidance Network (PGN), which can customize the encoded global guidance from Commander based on observations for each Soldier, providing each Soldier with specified guidance to the decision-making process. The Soldier takes into account not only the local actionobservation histories but also the specified guidance from PGN when making decisions. We validate CSRL on the challenging StarCraft II micromanagement benchmark, proving that our approach can take advantage of intermittent global information to improve collaborative performance. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52211] |
专题 | 综合信息系统研究中心_飞行器智能技术 |
通讯作者 | Hongxing Chang |
作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Chen YQ,Yang Wei,Tianle Zhang,et al. Commander-Soldiers Reinforcement Learning for Cooperative Multi-Agent Systems[C]. 见:. 意大利. 2022-7. |
个性服务 |
查看访问统计 |
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