Control of nonaffine nonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks

Qinmin Yang; Jonathan B. Vance; Jagannathan Sarangapani

doi:10.1109/TSMCB.2008.926607

Control of nonaffine nonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks

Qinmin Yang
, Jonathan B. Vance
, Jagannathan Sarangapani

Electrical and Computer Engineering

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

Original language	English
Pages (from-to)	994-1001
Number of pages	8
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	38
Issue number	4
DOIs	https://doi.org/10.1109/TSMCB.2008.926607
State	Published - Aug 2008

ASJC Scopus Subject Areas

Control and Systems Engineering
Software
Information Systems
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

Keywords

Adaptive critic
Adaptive dynamic programming
Lyapunov stability
Neural network control
Reinforcement learning control

Access to Document

10.1109/TSMCB.2008.926607

Cite this

Control of nonaffine nonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks. / Yang, Qinmin; Vance, Jonathan B.; Sarangapani, Jagannathan.
In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 38, No. 4, 08.2008, p. 994-1001.

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

@article{f3d47ed7bb5c4d539975dd6c9111ce27,

title = "Control of nonaffine nonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks",

keywords = "Adaptive critic, Adaptive dynamic programming, Lyapunov stability, Neural network control, Reinforcement learning control",

author = "Qinmin Yang and Vance, \{Jonathan B.\} and Jagannathan Sarangapani",

year = "2008",

month = aug,

doi = "10.1109/TSMCB.2008.926607",

language = "English",

volume = "38",

pages = "994--1001",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

number = "4",

}

TY - JOUR

T1 - Control of nonaffine nonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks

AU - Yang, Qinmin

AU - Vance, Jonathan B.

AU - Sarangapani, Jagannathan

PY - 2008/8

Y1 - 2008/8

KW - Adaptive critic

KW - Adaptive dynamic programming

KW - Lyapunov stability

KW - Neural network control

KW - Reinforcement learning control

UR - https://www.scopus.com/pages/publications/49049091364

UR - https://www.scopus.com/pages/publications/49049091364#tab=citedBy

U2 - 10.1109/TSMCB.2008.926607

DO - 10.1109/TSMCB.2008.926607

M3 - Article

C2 - 18632390

SN - 1083-4419

VL - 38

SP - 994

EP - 1001

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

IS - 4

ER -

Control of nonaffine nonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this