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6条，第1-6条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
Comprehensive comparison of online ADP algorithms for continuous-time optimal control 期刊论文
ARTIFICIAL INTELLIGENCE REVIEW, 2018, 卷号: 49, 期号: 4, 页码: 531-547
作者:  Zhu, Yuanheng;  Zhao, Dongbin
Adobe PDF(766Kb)  |  收藏  |  浏览/下载：413/183  |  提交时间：2017/09/13
Adaptive Dynamic Programming  Policy Iteration  Integral Reinforcement Learning  Experience Replay  Off-policy  
Online reinforcement learning for continuous-state systems 专著章节/文集论文
出自: Frontiers of Intelligent Control and Information Processing, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore, Singapore:World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, World Scientific, 2014
作者:  Yuanheng Zhu;  Zhao DB(赵冬斌)
Adobe PDF(24150Kb)  |  收藏  |  浏览/下载：250/27  |  提交时间：2017/09/13
Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 卷号: 28, 期号: 3, 页码: 714-725
作者:  Zhu, Yuanheng;  Zhao, Dongbin;  Li, Xiangjun
浏览  |  Adobe PDF(547Kb)  |  收藏  |  浏览/下载：448/186  |  提交时间：2017/05/05
Adaptive Dynamic Programming (Adp)  H-infinity Control  Policy Iteration (Pi)  Zero-sum Game (Zsg)  
Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 3, 页码: 854-865
作者:  Zhao, Dongbin;  Zhang, Qichao;  Wang, Ding;  Zhu, Yuanheng
浏览  |  Adobe PDF(1769Kb)  |  收藏  |  浏览/下载：512/197  |  提交时间：2016/06/14
Adaptive Dynamic Programming (Adp)  Experience Replay  Nonzero-sum (Nzs) Games  Optimal Control  Unknown Dynamics  
MEC-A Near-Optimal Online Reinforcement Learning Algorithm for Continuous Deterministic Systems 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 卷号: 26, 期号: 2, 页码: 346-356
作者:  Zhao, Dongbin;  Zhu, Yuanheng
浏览  |  Adobe PDF(2156Kb)  |  收藏  |  浏览/下载：272/111  |  提交时间：2015/09/18
Efficient Exploration  Probably Approximately Correct (Pac)  Reinforcement Learning (Rl)  State Aggregation  
连续状态系统的近似最优在线强化学习 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2015
作者:  朱圆恒
Adobe PDF(2679Kb)  |  收藏  |  浏览/下载：508/0  |  提交时间：2015/09/02
强化学习  最优控制  近似策略迭代  概率近似最优  连续状态系统  收敛性  在线学习  Kd树  Reinforcement Learning  Optimal Control  Approximate Policy Iteration  Probably Approximately Correct  Continuous-state System  Convergence  Online Learning  Kd-tree