中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共3条，第1-3条 帮助

限定条件                                
已选(0)清除 条数/页：   排序方式：
Learning and Guaranteed Cost Control With Event-Based Adaptive Critic Implementation 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 期号: 12, 页码: 6004-6014
作者:  Wang, Ding;  Liu, Derong
收藏  |  浏览/下载：292/0  |  提交时间：2019/07/12
Adaptive dynamic programming  event-based design  guaranteed cost control  optimal control  self-learning technique  
A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents 期刊论文
IEEE ACCESS, 2018, 卷号: 6, 页码: 70223-70235
作者:  Zhang, Zhen;  Wang, Dongqing;  Zhao, Dongbin;  Han, Qiaoni;  Song, Tingting
收藏  |  浏览/下载：281/0  |  提交时间：2019/07/12
Multi-agent reinforcement learning  gradient ascent  Q-learning  cooperative tasks  
Adaptive Q-Learning for Data-Based Optimal Output Regulation With Experience Replay 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2018, 卷号: 48, 期号: 12, 页码: 3337-3348
作者:  Luo, Biao;  Yang, Yin;  Liu, Derong
收藏  |  浏览/下载：330/0  |  提交时间：2019/01/08
Data-based  experience replay  neural networks (NNs)  off-policy  optimal control  Q-learning (QL)