中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共10条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Relaxed Stability Criteria for Time-Delay Systems: A Novel Quadratic Function Convex Approximation Approach 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 4, 页码: 996-1006
作者:  Shenquan Wang;  Wenchengyu Ji;  Yulian Jiang;  Yanzheng Zhu;  Jian Sun
Adobe PDF(2175Kb)  |  收藏  |  浏览/下载：67/19  |  提交时间：2024/03/18
Equivalent reciprocal combination technique  quadratic function convex approximation approach  stability  timevarying delay  
Data Generation Feedback Relearning Control for Unmodeled Nonlinear Systems 期刊论文
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2023, 页码: 12
作者:  Zhang, Yong;  Mu, Chaoxu;  Zhao, Dongbin
收藏  |  浏览/下载：118/0  |  提交时间：2023/11/16
Data models  Real-time systems  Heuristic algorithms  Mathematical models  Adaptation models  Approximation algorithms  Cost function  Data generation model  feedback relearning control  delayed neural network  reinforcement learning  unmodeled nonlinear system  
Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space 期刊论文
ARTIFICIAL INTELLIGENCE REVIEW, 2021, 页码: 36
作者:  Yang, Yongliang;  Zhu, Hufei;  Zhang, Qichao;  Zhao, Bo;  Li, Zhenning;  Wunsch, Donald C.
收藏  |  浏览/下载：238/0  |  提交时间：2021/11/02
Reproducing kernel Hilbert space  Actor-critic learning  Value function approximation  Online sparsification  Non-parametric learning  
Solving Trajectory Optimization Problems in the Presence of Probabilistic Constraints 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2020, 卷号: 50, 期号: 10, 页码: 4332-4345
作者:  Chai, Runqi;  Savvaris, Al;  Tsourdos, Antonios;  Chai, Senchun;  Xia, Yuanqing;  Wang, Shuo
收藏  |  浏览/下载：226/0  |  提交时间：2021/01/07
Planning  Probabilistic logic  Trajectory optimization  Optimal control  Prediction algorithms  Approximation function  chance-constrained  nonlinear programming  probabilistic constraints  trajectory optimization  
Universal Approximation Capability of Broad Learning System and Its Structural Variations 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 卷号: 30, 期号: 4, 页码: 1191-1204
作者:  Chen, C. L. Philip;  Liu, Zhulin;  Feng, Shuang
收藏  |  浏览/下载：278/0  |  提交时间：2019/12/16
Broad learning system (BLS)  deep learning  face recognition  functional link neural networks (FLNNs)  non-linear function approximation  time-variant big data modeling  universal approximation  
Adaptive dynamic programming for robust neural control of unknown continuous-time non-linear systems 期刊论文
IET CONTROL THEORY AND APPLICATIONS, 2017, 卷号: 11, 期号: 14, 页码: 2307-2316
作者:  Yang, Xiong;  He, Haibo;  Liu, Derong;  Zhu, Yuanheng
浏览  |  Adobe PDF(2123Kb)  |  收藏  |  浏览/下载：479/152  |  提交时间：2017/09/13
Dynamic Programming  Robust Control  Neurocontrollers  Continuous Time Systems  Control System Synthesis  Nonlinear Control Systems  Optimal Control  Function Approximation  Monte Carlo Methods  Closed Loop Systems  Asymptotic Stability  Adaptive Dynamic Programming  Robust Neural Control Design  Unknown Continuous-time Nonlinear Systems  Ct Nonlinear Systems  Adp-based Robust Neural Control Scheme  Robust Nonlinear Control Problem  Nonlinear Optimal Control Problem  Nominal System  Adp Algorithm  Actor-critic Dual Networks  Control Policy Approximation  Value Function Approximation  Actor Neural Network Weights  Critic Nn Weights  Monte Carlo Integration Method  Closed-loop System  Asymptotically Stability  
Echo state network-based Q-learning method for optimal battery control of offices combined with renewable energy 期刊论文
IET CONTROL THEORY AND APPLICATIONS, 2017, 卷号: 11, 期号: 7, 页码: 915-922
作者:  Shi, Guang;  Liu, Derong;  Wei, Qinglai
浏览  |  Adobe PDF(3253Kb)  |  收藏  |  浏览/下载：457/138  |  提交时间：2017/02/23
Recurrent Neural Nets  Neurocontrollers  Learning (Artificial Intelligence)  Office Environment  Optimal Control  Solar Power  Energy Consumption  Time Series  Secondary Cells  Energy Management Systems  Function Approximation  Echo State Network-based Q-learning Method  Optimal Battery Control  Renewable Energy  Optimal Energy Management  Solar Energy  Energy Consumption  Energy Demand  Time Series  Real-time Electricity Rate  Periodic Functions  Q-function  Optimal Charging Strategy  Optimal Discharging Strategy  Optimal Idle Strategy  Numerical Analysis  
PID controller design for output PDFs of stochastic systems using linear matrix inequalities 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2005, 卷号: 35, 期号: 1, 页码: 65-71
作者:  Guo, L;  Wang, H
收藏  |  浏览/下载：139/0  |  提交时间：2015/11/06
B-spline Approximation  Convex Optimization  Probability Density Function  Proportional-integral-derivative (Pid) Control  Stochastic Systems  Tracking Performance  
增强学习的理论和在路径规划问题中的应用 学位论文
, 中国科学院自动化研究所: 中国科学院研究生院, 2003
作者:  汤俏
Adobe PDF(3837Kb)  |  收藏  |  浏览/下载：168/0  |  提交时间：2015/09/02
增强学习  函数逼近  直接增强学习  多主体  Reinforcement Leaming  Function Approximation  Direct Reinforcement Learning  Multi-agent System  
连续状态-动作空间下强化学习方法的研究 学位论文
, 中国科学院自动化研究所: 中国科学院研究生院, 2005
作者:  程玉虎
收藏  |  浏览/下载：554/0  |  提交时间：2015/09/02
强化学习  连续空间  函数逼近  Rbf 网络  模糊推理系统  Reinforcement Learning  Continuous Space  Function Approximation  Rbf Network  Fuzzy Inference System