中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共2条，第1-2条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
A data-based online reinforcement learning algorithm satisfying probably approximately correct principle 期刊论文
NEURAL COMPUTING & APPLICATIONS, 2015, 卷号: 26, 期号: 4, 页码: 775-787
作者:  Zhu, Yuanheng;  Zhao, Dongbin
Adobe PDF(1331Kb)  |  收藏  |  浏览/下载：283/63  |  提交时间：2015/09/21
Reinforcement Learning  Probably Approximately Correct  Kd-tree  
A neural-network-based iterative GDHP approach for solving a class of nonlinear optimal control problems with control constraints 期刊论文
NEURAL COMPUTING & APPLICATIONS, 2013, 卷号: 22, 期号: 2, 页码: 219-227
作者:  Wang, Ding;  Liu, Derong;  Zhao, Dongbin;  Huang, Yuzhu;  Zhang, Dehua
Adobe PDF(507Kb)  |  收藏  |  浏览/下载：267/78  |  提交时间：2015/08/12
Adaptive Critic Designs  Adaptive Dynamic Programming  Approximate Dynamic Programming  Neural Dynamic Programming  Neural Networks  Optimal Control  Reinforcement Learning