Knowledge Commons of Institute of Automation,CAS
Hierarchical Cooperative Swarm Policy Learning with Role Emergence | |
Zhang TL(张天乐)1,2; Liu Z(刘振)1,2; Pu ZQ(蒲志强)1,2; Qiu TH(丘腾海)1,2; Yi JQ(易建强)1,2 | |
2021 | |
会议名称 | IEEE Symposium Series on Computational Intelligence |
会议日期 | 05-07 December 2021 |
会议地点 | Online |
出版者 | IEEE |
摘要 | Swarm systems can cooperatively and efficiently accomplish specified complex tasks. Recent works have shown the potential of multi-agent reinforcement learning methods to study behavior policies of swarm systems. However, it is difficult for them to complete complex swarm tasks efficiently. In human society, role assignment can effectively help humans understand complex tasks and decompose them into simple certain subtasks. Inspired by this, we propose a two-level hierarchical cooperative swarm policy learning framework with role emergence based on hierarchical deep reinforcement learning for distributed swarm systems. In this framework, roles are dynamic and emergent. Agents with the same role tend to collectively complete a certain subtask. Specifically, each agent uses a higher-level swarm policy to dynamically select a role for itself in a role space and at a higher temporal scale, while it uses a lower-level swarm policy to perform the responsibilities of the selected role in a primitive action space. Meanwhile, hierarchical swarm policies with partial observation are centrally trained and decentrally executed, where agents’ local interaction modules and extrinsic team rewards are designed to promote cooperation among agents. In addition, an intrinsic reward is defined to enable different roles to be identified by agents’ longer-term behaviors, which implicitly associates the roles with responsibilities. Simulation results show that our method can learn and generate emergent, dynamic and identifiable roles, which helps swarm systems to reliably and efficiently accomplish complex tasks in a shorter time. |
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/173211/51964 |
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 |
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. Hierarchical Cooperative Swarm Policy Learning with Role Emergence[C]:IEEE,2021. |
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 | ||
2021-SSCI.pdf(327KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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