中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共4条，第1-4条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
A Self-Attention-Based Deep Reinforcement Learning Approach for AGV Dispatching Systems 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 12
作者:  Wei, Qinglai;  Yan, Yutian;  Zhang, Jie;  Xiao, Jun;  Wang, Cong
收藏  |  浏览/下载：211/0  |  提交时间：2023/01/09
Automated guided vehicle (AGV) dispatching  deep learning  reinforcement learning (RL)  self-attention  
VGN: Value Decomposition With Graph Attention Networks for Multiagent Reinforcement Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 14
作者:  Wei, Qinglai;  Li, Yugu;  Zhang, Jie;  Wang, Fei-Yue
收藏  |  浏览/下载：215/0  |  提交时间：2022/07/25
Mathematical models  Task analysis  Games  Q-learning  Neural networks  Behavioral sciences  Training  Deep learning  graph attention networks (GATs)  multiagent systems  reinforcement learning  
Model-Free Adaptive Optimal Control for Unknown Nonlinear Multiplayer Nonzero-Sum Game 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 卷号: 33, 期号: 2, 页码: 879-892
作者:  Wei, Qinglai;  Zhu, Liao;  Song, Ruizhuo;  Zhang, Pinjia;  Liu, Derong;  Xiao, Jun
收藏  |  浏览/下载：246/0  |  提交时间：2022/03/17
Heuristic algorithms  Nonlinear systems  Optimal control  Mathematical model  Dynamic programming  Games  Adaptive systems  Adaptive dynamic programming (ADP)  globalized dual-heuristic dynamic programming (GDHP)  multiplayer nonzero-sum game (MP-NZSG)  neural network (NN)  
Spiking Adaptive Dynamic Programming Based on Poisson Process for Discrete-Time Nonlinear Systems 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 11
作者:  Wei, Qinglai;  Han, Liyuan;  Zhang, Tielin
收藏  |  浏览/下载：171/0  |  提交时间：2022/01/27
Process control  Control systems  Optimal control  Maximum likelihood estimation  Performance analysis  Dynamic programming  Nonlinear systems  Maximum likelihood estimation (MLE)  nonlinear systems  optimal control  Poisson process  spike train  spiking adaptive dynamic programming (SADP)