设为首页
收藏本站
网站地图
|
English
|
公务邮箱
About the library
Background
History
Leadership
Organization
Readers' Guide
Opening Hours
Collections
Help Via Email
Publications
Electronic Information Resources
常用资源
电子图书
期刊论文
学位会议
外文资源
特色专题
内部出版物
Springer电子图书(2)
ProQuest学位论文(16)
ACS电子期刊(2)
SpringerLink电子期刊(137)
Elsevier电子期刊(105)
在“
Elsevier电子期刊
”中,
命中:
105
条,耗时:0.0340128 秒
在所有数据库中总计命中:
262
条
1.
Optimal learning control of oxygen saturation using a
policy
iteration
algorithm
and a proof-of-concept in an interconnecting three-tank system
作者:
Anake Pomprapa
;
pomprapa@hia.rwth-aachen.de
;
Steffen Leonhardt
;
Berno J.E. Misgeld
关键词:
Policy
iteration
algorithm
;
Optimal control
;
Reinforcement learning
;
Control of oxygen saturation
;
Biomedical control system
;
Closed-loop ventilation
刊名:Control Engineering Practice
出版年:2017
2.
Value set
iteration
for two-person zero-sum Markov games
作者:
Hyeong Soo Chang
1
;
hschang@sogang.ac.kr
关键词:
Two-person zero-sum Markov game
;
Value
iteration
;
Policy
iteration
;
Stochastic game
刊名:Automatica
出版年:2017
3.
Online fitted
policy
iteration
based on extreme learning machines
作者:
Pablo Escandell-Montero
;
a
;
pablo.escandell@uv.es" class="auth_mail" title="E-mail the corresponding author
;
Delia Lorente
b
;
José
;
M. Martí
;
nez-Martí
;
nez
a
;
Emilio Soria-Olivas
a
;
Joan Vila-Francé
;
s
a
;
José
;
D. Martí
;
n-Guerrero
a
关键词:
Reinforcement learning
;
Sequential decision-making
;
Fitted
policy
iteration
;
Extreme learning machine
刊名:Knowledge-Based Systems
出版年:2016
4.
Improved bound on the worst case complexity of
Policy
Iteration
作者:
Romain Hollanders
;
romain.hollanders@gmail.com" class="auth_mail" title="E-mail the corresponding author
;
Balá
;
zs Gerencsé
;
r
balazs.gerencser@uclouvain.be" class="auth_mail" title="E-mail the corresponding author
;
Jean-Charles Delvenne
1
;
jean-charles.delvenne@uclouvain.be" class="auth_mail" title="E-mail the corresponding author
;
Raphaë
;
l M. Jungers
2
;
raphael.jungers@uclouvain.be" class="auth_mail" title="E-mail the corresponding author
关键词:
Policy
Iteration
;
Complexity
;
Markov Decision Process
;
Acyclic Unique Sink Orientation
刊名:Operations Research Letters
出版年:2016
5.
Traffic Signal Control based on Markov Decision Process
*
作者:
Yunwen Xu
*
;
willing419@sjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author
;
Yugeng Xi
*
;
ygxi@sjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author
;
Dewei Li
*
;
dwli@sjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author
;
Zhao Zhou
*
;
zzhou553@gmail.com" class="auth_mail" title="E-mail the corresponding author
关键词:
Markov state transition model
;
Traffic signal control
;
Policy
iteration
algorithm
;
Markov decision process
刊名:IFAC-PapersOnLine
出版年:2016
6.
Online finite-horizon optimal learning
algorithm
for nonzero-sum games with partially unknown dynamics and constrained inputs
作者:
Xiaohong Cui
a
;
b
;
xiaohong19821206@126.com" class="auth_mail" title="E-mail the corresponding author
Author Vitae
;
Huaguang Zhang
a
;
hgzhang@ieee.org" class="auth_mail" title="E-mail the corresponding author
Author Vitae
;
Yanhong Luo
a
;
neuluo@gmail.com" class="auth_mail" title="E-mail the corresponding author
Author Vitae
;
Peifu Zu
b
;
zpf007007@163.com" class="auth_mail" title="E-mail the corresponding author
Author Vitae
关键词:
Finite-horizon
;
Nonzero-sum games
;
Neural network
;
Adaptive dynamic programming
刊名:Neurocomputing
出版年:2016
7.
Data-based fault-tolerant control for affine nonlinear systems with actuator faults
作者:
Chun-Hua Xie
a
;
xie.chun_hua@163.com" class="auth_mail" title="E-mail the corresponding author
;
Guang-Hong Yang
a
;
b
;
yangguanghong@ise.neu.edu.cn" class="auth_mail" title="E-mail the corresponding author
关键词:
Unknown nonlinear systems
;
Data-based
policy
iteration
algorithm
;
Fault-tolerant control
;
Actuator faults
刊名:ISA Transactions
出版年:2016
8.
Policy
Derivation Methods for Critic-Only Reinforcement Learning in Continuous Action Spaces
作者:
Eduard Alibekov
*
;
eduard.alibekov@cvut.cz" class="auth_mail" title="E-mail the corresponding author
;
Jiri Kubalik
*
;
jiri.kubalik@cvut.cz" class="auth_mail" title="E-mail the corresponding author
;
Robert Babuska
*
;
**
;
r.babuska@tudelft.nl" class="auth_mail" title="E-mail the corresponding author
关键词:
reinforcement learning
;
continuous actions
;
multi-variable systems
;
optimal control
;
policy
derivation
刊名:IFAC-PapersOnLine
出版年:2016
9.
Value
iteration
and adaptive dynamic programming for data-driven adaptive optimal control design
作者:
Tao Bian
1
;
tbian@nyu.edu" class="auth_mail" title="E-mail the corresponding author
Author Vitae
;
Zhong-Ping Jiang
zjiang@nyu.edu" class="auth_mail" title="E-mail the corresponding author
Author Vitae
关键词:
Value
iteration
;
Adaptive dynamic programming
;
Optimal control
;
Adaptive control
;
Stochastic approximation
刊名:Automatica
出版年:2016
10.
Data-based robust optimal control of continuous-time affine nonlinear systems with matched uncertainties
作者:
Ding Wang
;
a
;
c
;
ding.wang@ia.ac.cn" class="auth_mail" title="E-mail the corresponding author
;
Chao Li
a
;
lichao2012@ia.ac.cn" class="auth_mail" title="E-mail the corresponding author
;
Derong Liu
b
;
derong@ustb.edu.cn" class="auth_mail" title="E-mail the corresponding author
;
Chaoxu Mu
c
;
cxmu@tju.edu.cn" class="auth_mail" title="E-mail the corresponding author
关键词:
Adaptive dynamic programming
;
Data-based control
;
Integral
policy
iteration
;
Matched uncertainties
;
Neural networks
;
Robust optimal control
刊名:Information Sciences
出版年:2016
1
2
3
4
5
6
7
8
9
按检索点细分(105)
题名(3)
关键词(14)
文摘(91)
按出版年细分(105)
2027年及以后(9)
2017年(2)
2016年(13)
2015年(3)
2014年(2)
2013年(11)
2012年(9)
2011年(12)
2010年(3)
2009年(8)
2008年(6)
2007年(6)
2006年(4)
2005年(2)
2004年(1)
2002年(1)
2001年(2)
2000年及以前(11)
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via
email
.