中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页
机构
成果
学者
登录
注册
登陆
×
验证码:
换一张
忘记密码?
记住我
×
校外用户登录
CAS IR Grid
机构
自动化研究所 [3]
计算技术研究所 [1]
采集方式
OAI收割 [4]
内容类型
期刊论文 [4]
发表日期
2022 [4]
学科主题
筛选
浏览/检索结果:
共4条,第1-4条
帮助
限定条件
发表日期:2022
条数/页:
5
10
15
20
25
30
35
40
45
50
55
60
65
70
75
80
85
90
95
100
排序方式:
请选择
题名升序
题名降序
提交时间升序
提交时间降序
作者升序
作者降序
发表日期升序
发表日期降序
Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network
期刊论文
OAI收割
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 10
作者:
Du, Wei
;
Ding, Shifei
;
Zhang, Chenglong
;
Shi, Zhongzhi
  |  
收藏
  |  
浏览/下载:7/0
  |  
提交时间:2023/07/12
Reinforcement learning
Multi-agent systems
Aggregates
Task analysis
Scalability
Marine vehicles
Learning systems
Graph attention network
heterogeneous agents
multiagent reinforcement learning (MARL)
relationship-level attention
Attention Enhanced Reinforcement Learning for Multi agent Cooperation
期刊论文
OAI收割
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 15
作者:
Pu, Zhiqiang
;
Wang, Huimu
;
Liu, Zhen
;
Yi, Jianqiang
;
Wu, Shiguang
  |  
收藏
  |  
浏览/下载:30/0
  |  
提交时间:2022/06/06
Training
Reinforcement learning
Games
Scalability
Task analysis
Standards
Optimization
Attention mechanism
deep reinforcement learning (DRL)
graph convolutional networks
multi agent systems
Attention enhanced reinforcement learning for multi-agent cooperation
期刊论文
OAI收割
IEEE Transactions on Neural Networks and Learning Systems, 2022, 期号: 2022, 页码: 1-15
作者:
Zhiqiang Pu
;
Huimu Wang
;
Zhen Liu
;
Jianqiang Yi
;
Shiguang Wu
  |  
收藏
  |  
浏览/下载:12/0
  |  
提交时间:2022/04/02
Attention mechanism
deep reinforcement learning (DRL)
graph convolutional networks
multi agent systems
Efficient Exploration for Multi-Agent Reinforcement Learning via Transferable Successor Features
期刊论文
OAI收割
IEEE/CAA Journal of Automatica Sinica, 2022, 卷号: 9, 期号: 9, 页码: 1673-1686
作者:
Wenzhang Liu
;
Lu Dong
;
Dan Niu
;
Changyin Sun
  |  
收藏
  |  
浏览/下载:14/0
  |  
提交时间:2022/08/19
Knowledge transfer
multi-agent systems
reinforcement learning
successor features