CASIA OpenIR  > 综合信息系统研究中心  > 飞行器智能技术
Multi-Agent Cognition Difference Reinforcement Learning for MultiAgent Cooperation
Huimu, Wang1,2; Tenghai, Qiu2; Zhen, Liu2; Zhiqiang, Pu1,2; Jianqiang, Yi1,2; Wanmai Yuan3
2021-07
会议名称International Joint Conference on Neural Networks
会议日期2021-07
会议地点线上
摘要

Multi-agent cooperation is one of the most attractive research fields in multi-agent systems. There are many attempts made by researchers in this field to promote the cooperation behavior. However, in partially-observable environments, a large number of agents and complex interactions among the agents cause huge difficulty for policy learning. Moreover, redundant
communication contents caused by many agents make effective features hard to be extracted, which prevents the policy from converging. To address the limitations above, a novel method called multi-agent cognition difference reinforcement learning (MACD-RL) is proposed in this paper. The key feature of MACD-RL lies in cognition difference network (CDN) and a soft communication network (SCN). CDN is designed to allow each
agent to choose its neighbors (communication targets) adaptively with its environment cognition difference. SCN is designed to handle the complex interactions among the agents with soft attention mechanism. The results of simulations including mixed cooperative and competitive tasks demonstrate that the effectiveness and robustness of the proposed model.
 

收录类别EI
语种英语
七大方向——子方向分类强化与进化学习
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/44954
专题综合信息系统研究中心_飞行器智能技术
通讯作者Tenghai, Qiu
作者单位1.School of Artificial Intelligence, University of Chinese Academy of Sciences
2.Institute of Automation, Chinese Academy of Sciences
3.China Academy of Electronics and Information Technology
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
Huimu, Wang,Tenghai, Qiu,Zhen, Liu,et al. Multi-Agent Cognition Difference Reinforcement Learning for MultiAgent Cooperation[C],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
conference_101719.pd(478KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Huimu, Wang]的文章
[Tenghai, Qiu]的文章
[Zhen, Liu]的文章
百度学术
百度学术中相似的文章
[Huimu, Wang]的文章
[Tenghai, Qiu]的文章
[Zhen, Liu]的文章
必应学术
必应学术中相似的文章
[Huimu, Wang]的文章
[Tenghai, Qiu]的文章
[Zhen, Liu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: conference_101719.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。