Knowledge Commons of Institute of Automation,CAS
Multi-Agent Cooperation and Competition with Two-Level Ggraph Attention Network | |
Shiguang, Wu1,2; Zhiqiang, Pu1,2; Jianqiang, Yi1,2; Huimu, Wang1,2 | |
2020-11 | |
会议名称 | The 27th International Conference on Neural Information Processing |
会议日期 | 2020-11 |
会议地点 | 线上 |
摘要 | Multi-agent reinforcement learning (MARL) has made significant advances in multi-agent systems. However, it is hard to learn a stable policy in complicated and changeable environment. To address these issues, a two-level attention network is proposed, which is composed of across-group observation attention network (AGONet) and intentional communication network (ICN). AGONet is designed to distinguish the different semantic meanings of observations (including friend group, foe group, and object/entity group) and extract different underlying information of different groups with across-group attention. Based AGONet, the proposed network framework is invariant to the number of agents existing in the system, which can be applied in large-scale multi-agent systems. Furthermore, to enhance the cooperation of the agents in the same group, ICN is used to aggregate the intentions of neighbors in the same group, which are extracted by AGONet. It obtains the understanding and intentions of their neighbors in the same group and enlarges the receptive filed of the agent. The simulation results demonstrate that the agents can learn complicated cooperative and competitive strategies and our method is superiority to existing methods. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 多智能体系统 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44960 |
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 | Zhiqiang, Pu |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences |
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 | Shiguang, Wu,Zhiqiang, Pu,Jianqiang, Yi,et al. Multi-Agent Cooperation and Competition with Two-Level Ggraph Attention Network[C],2020. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Wu2020_Chapter_Multi(1185KB) | 会议论文 | 暂不开放 | CC BY-NC-SA |
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