咨询与建议

限定检索结果

文献类型

  • 9 篇 会议
  • 8 篇 期刊文献

馆藏范围

  • 17 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 17 篇 工学
    • 11 篇 计算机科学与技术...
    • 9 篇 控制科学与工程
    • 4 篇 软件工程
    • 3 篇 电气工程
    • 1 篇 航空宇航科学与技...
  • 6 篇 管理学
    • 6 篇 管理科学与工程(可...
  • 1 篇 理学
    • 1 篇 数学
    • 1 篇 系统科学
  • 1 篇 医学
    • 1 篇 基础医学(可授医学...
    • 1 篇 临床医学

主题

  • 17 篇 dual heuristic d...
  • 8 篇 adaptive dynamic...
  • 4 篇 reinforcement le...
  • 4 篇 dhp
  • 3 篇 neural network
  • 2 篇 heuristic dynami...
  • 2 篇 stability analys...
  • 2 篇 value-gradient l...
  • 1 篇 approximate dyna...
  • 1 篇 mixed-mode conve...
  • 1 篇 nonquadratic
  • 1 篇 motivation
  • 1 篇 value iteration
  • 1 篇 online sequentia...
  • 1 篇 event-based cont...
  • 1 篇 image transforma...
  • 1 篇 underactuated sy...
  • 1 篇 wiped film molec...
  • 1 篇 critical slip su...
  • 1 篇 ball and beam sy...

机构

  • 2 篇 northeastern uni...
  • 2 篇 beijing univ tec...
  • 2 篇 department of co...
  • 2 篇 guangdong univ t...
  • 1 篇 city univ london...
  • 1 篇 yonsei univ sch ...
  • 1 篇 guangxi univ col...
  • 1 篇 chinese acad sci...
  • 1 篇 beijing univ tec...
  • 1 篇 northeastern uni...
  • 1 篇 jilin univ coll ...
  • 1 篇 natl key lab sci...
  • 1 篇 univ memphis dep...
  • 1 篇 northeastern uni...
  • 1 篇 beijing aerosp a...
  • 1 篇 univ sci & techn...
  • 1 篇 univ sci & techn...
  • 1 篇 city univ london...
  • 1 篇 beijing univ tec...
  • 1 篇 beijing aerosp a...

作者

  • 3 篇 wang ding
  • 2 篇 wang zhaolei
  • 2 篇 alonso eduardo
  • 2 篇 zhang huaguang
  • 2 篇 szuster marcin
  • 2 篇 ha mingming
  • 2 篇 liu jiarun
  • 2 篇 liu derong
  • 2 篇 eduardo alonso
  • 2 篇 yan ying
  • 2 篇 fairbank michael
  • 2 篇 michael fairbank
  • 2 篇 huang xu
  • 2 篇 sun jiayue
  • 1 篇 burghardt andrze...
  • 1 篇 choi yoon ho
  • 1 篇 hendzel zenon
  • 1 篇 zhao bo
  • 1 篇 huang qingbao
  • 1 篇 song shaojian

语言

  • 16 篇 英文
  • 1 篇 其他
检索条件"主题词=Dual Heuristic Dynamic Programming"
17 条 记 录,以下是11-20 订阅
Approximate dynamic programming in Tracking Control of a Robotic Manipulator
收藏 引用
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2016年 第1期13卷 16-16页
作者: Szuster, Marcin Gierlak, Piotr Rzeszow Univ Technol Rzeszow Poland
This article focuses on the implementation of an approximate dynamic programming algorithm in the discrete tracking control system of the three-degrees of freedom Scorbot-ER 4pc robotic manipulator. The controlled sys... 详细信息
来源: 评论
Reinforcement Learning in Discrete Neural Control of the Underactuated System
Reinforcement Learning in Discrete Neural Control of the Und...
收藏 引用
12th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2013
作者: Hendzel, Zenon Burghardt, Andrzej Szuster, Marcin Rzeszow Univ Technol Dept Appl Mech & Robot PL-35959 Rzeszow Poland
The article presents a new approach to the problem of a discrete neural control of an underactuated system, using reinforcement learning method to an on-line adaptation of a neural network. The controlled system is of... 详细信息
来源: 评论
Value-Gradient Learning
Value-Gradient Learning
收藏 引用
IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)/International Joint Conference on Neural Networks (IJCNN)/IEEE Congress on Evolutionary Computation (IEEE-CEC)/IEEE World Congress on Computational Intelligence (IEEE-WCCI)
作者: Fairbank, Michael Alonso, Eduardo City Univ London Sch Informat Dept Comp London EC1V 0HB England
We describe an Adaptive dynamic programming algorithm VGL(lambda) for learning a critic function over a large continuous state space. The algorithm, which requires a learned model of the environment, extends dual Heur... 详细信息
来源: 评论
A Comparison of Learning Speed and Ability to Cope Without Exploration between DHP and TD(0)
A Comparison of Learning Speed and Ability to Cope Without E...
收藏 引用
International Joint Conference on Neural Networks (IJCNN)
作者: Fairbank, Michael Alonso, Eduardo City Univ London Dept Comp Sch Informat London EC1V 0HB England
This paper demonstrates the principal motivations for dual heuristic dynamic programming (DHP) learning methods for use in Adaptive dynamic programming and Reinforcement Learning, in continuous state spaces: that of a... 详细信息
来源: 评论
A Comparison of Learning Speed and Ability to Cope Without Exploration between DHP and TD(0)
A Comparison of Learning Speed and Ability to Cope Without E...
收藏 引用
International Joint Conference on Neural Networks
作者: Michael Fairbank Eduardo Alonso Department of Computing School of Informatics City University London
This paper demonstrates the principal motivations for dual heuristic dynamic programming (DHP) learning methods for use in Adaptive dynamic programming and Reinforcement Learning, in continuous state spaces: that of a... 详细信息
来源: 评论
Value-Gradient Learning
Value-Gradient Learning
收藏 引用
International Joint Conference on Neural Networks
作者: Michael Fairbank Eduardo Alonso Department of Computing School of Informatics City University London
We describe an Adaptive dynamic programming algorithm VGL(λ) for learning a critic function over a large continuous state space. The algorithm, which requires a learned model of the environment, extends dual Heuristi... 详细信息
来源: 评论
Transformation Invariant On-Line Target Recognition
收藏 引用
IEEE TRANSACTIONS ON NEURAL NETWORKS 2011年 第6期22卷 906-918页
作者: Iftekharuddin, Khan M. Univ Memphis Dept Elect & Comp Engn Intelligent Syst & Image Proc Lab Memphis TN 38152 USA
Transformation invariant automatic target recognition (ATR) has been an active research area due to its widespread applications in defense, robotics, medical imaging and geographic scene analysis. The primary goal for... 详细信息
来源: 评论