Online optimal control of affine nonlinear discrete-time systems with unknown internal dynamics by using time-based policy update

Travis Dierks; Sarangapani Jagannathan

doi:10.1109/TNNLS.2012.2196708

Online optimal control of affine nonlinear discrete-time systems with unknown internal dynamics by using time-based policy update

Travis Dierks
, Sarangapani Jagannathan

Electrical and Computer Engineering

DRS Sustainment Systems Inc.

Research output: Contribution to journal › Article › peer-review

Original language	English
Article number	6208889
Pages (from-to)	1118-1129
Number of pages	12
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	23
Issue number	7
DOIs	https://doi.org/10.1109/TNNLS.2012.2196708
State	Published - 2012

ASJC Scopus Subject Areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Keywords

Hamilton-Jacobi-Bellman
online approximators
online nonlinear optimal control
time-based policy update

Access to Document

10.1109/TNNLS.2012.2196708

Cite this

@article{15daae854a58415fb009b02754137f27,

title = "Online optimal control of affine nonlinear discrete-time systems with unknown internal dynamics by using time-based policy update",

keywords = "Hamilton-Jacobi-Bellman, online approximators, online nonlinear optimal control, time-based policy update",

author = "Travis Dierks and Sarangapani Jagannathan",

year = "2012",

doi = "10.1109/TNNLS.2012.2196708",

language = "English",

volume = "23",

pages = "1118--1129",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

number = "7",

}

TY - JOUR

T1 - Online optimal control of affine nonlinear discrete-time systems with unknown internal dynamics by using time-based policy update

AU - Dierks, Travis

AU - Jagannathan, Sarangapani

PY - 2012

Y1 - 2012

KW - Hamilton-Jacobi-Bellman

KW - online approximators

KW - online nonlinear optimal control

KW - time-based policy update

UR - https://www.scopus.com/pages/publications/84875270081

UR - https://www.scopus.com/pages/publications/84875270081#tab=citedBy

U2 - 10.1109/TNNLS.2012.2196708

DO - 10.1109/TNNLS.2012.2196708

M3 - Article

AN - SCOPUS:84875270081

SN - 2162-237X

VL - 23

SP - 1118

EP - 1129

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 7

M1 - 6208889

ER -

Online optimal control of affine nonlinear discrete-time systems with unknown internal dynamics by using time-based policy update

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this