Integral reinforcement learning with explorations for continuous-time nonlinear systems

Jae Young Lee; Jin Bae Park; Yoon Ho Choi

doi:10.1109/IJCNN.2012.6252508

Integral reinforcement learning with explorations for continuous-time nonlinear systems

Jae Young Lee, Jin Bae Park, Yoon Ho Choi

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Citations (Scopus)

Abstract

This paper focuses on the integral reinforcement learning (I-RL) for input-affine continuous-time (CT) nonlinear systems where a known time-varying signal called an exploration is injected through the control input. First, we propose a modified I-RL method which effectively eliminates the effects of the explorations on the algorithm. Next, based on the result, an actor-critic I-RL technique is presented for the same nonlinear systems with completely unknown dynamics. Finally, the least-squares implementation method with the exact parameterizations is presented for each proposed one which can be solved under the given persistently exciting (PE) conditions. A simulation example is given to verify the effectiveness of the proposed methods.

Original language	English
Title of host publication	2012 International Joint Conference on Neural Networks, IJCNN 2012
DOIs	https://doi.org/10.1109/IJCNN.2012.6252508
Publication status	Published - 2012
Event	2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD, Australia Duration: 2012 Jun 10 → 2012 Jun 15

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Other

Other	2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
Country	Australia
City	Brisbane, QLD
Period	12/6/10 → 12/6/15

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2012.6252508

Fingerprint Dive into the research topics of 'Integral reinforcement learning with explorations for continuous-time nonlinear systems'. Together they form a unique fingerprint.

Cite this

@inproceedings{045aa140e2b04e10bb25847d5aab4f0a,

title = "Integral reinforcement learning with explorations for continuous-time nonlinear systems",

abstract = "This paper focuses on the integral reinforcement learning (I-RL) for input-affine continuous-time (CT) nonlinear systems where a known time-varying signal called an exploration is injected through the control input. First, we propose a modified I-RL method which effectively eliminates the effects of the explorations on the algorithm. Next, based on the result, an actor-critic I-RL technique is presented for the same nonlinear systems with completely unknown dynamics. Finally, the least-squares implementation method with the exact parameterizations is presented for each proposed one which can be solved under the given persistently exciting (PE) conditions. A simulation example is given to verify the effectiveness of the proposed methods.",

author = "Lee, {Jae Young} and Park, {Jin Bae} and Choi, {Yoon Ho}",

note = "Copyright: Copyright 2012 Elsevier B.V., All rights reserved.; 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 ; Conference date: 10-06-2012 Through 15-06-2012",

year = "2012",

doi = "10.1109/IJCNN.2012.6252508",

language = "English",

isbn = "9781467314909",

series = "Proceedings of the International Joint Conference on Neural Networks",

booktitle = "2012 International Joint Conference on Neural Networks, IJCNN 2012",

}

Lee, JY, Park, JB & Choi, YH 2012, Integral reinforcement learning with explorations for continuous-time nonlinear systems. in 2012 International Joint Conference on Neural Networks, IJCNN 2012., 6252508, Proceedings of the International Joint Conference on Neural Networks, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, Australia, 12/6/10. https://doi.org/10.1109/IJCNN.2012.6252508

Integral reinforcement learning with explorations for continuous-time nonlinear systems. / Lee, Jae Young; Park, Jin Bae; Choi, Yoon Ho.

2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012. 6252508 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Integral reinforcement learning with explorations for continuous-time nonlinear systems

AU - Lee, Jae Young

AU - Park, Jin Bae

AU - Choi, Yoon Ho

PY - 2012

Y1 - 2012

N2 - This paper focuses on the integral reinforcement learning (I-RL) for input-affine continuous-time (CT) nonlinear systems where a known time-varying signal called an exploration is injected through the control input. First, we propose a modified I-RL method which effectively eliminates the effects of the explorations on the algorithm. Next, based on the result, an actor-critic I-RL technique is presented for the same nonlinear systems with completely unknown dynamics. Finally, the least-squares implementation method with the exact parameterizations is presented for each proposed one which can be solved under the given persistently exciting (PE) conditions. A simulation example is given to verify the effectiveness of the proposed methods.

AB - This paper focuses on the integral reinforcement learning (I-RL) for input-affine continuous-time (CT) nonlinear systems where a known time-varying signal called an exploration is injected through the control input. First, we propose a modified I-RL method which effectively eliminates the effects of the explorations on the algorithm. Next, based on the result, an actor-critic I-RL technique is presented for the same nonlinear systems with completely unknown dynamics. Finally, the least-squares implementation method with the exact parameterizations is presented for each proposed one which can be solved under the given persistently exciting (PE) conditions. A simulation example is given to verify the effectiveness of the proposed methods.

UR - http://www.scopus.com/inward/record.url?scp=84865092901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865092901&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2012.6252508

DO - 10.1109/IJCNN.2012.6252508

M3 - Conference contribution

AN - SCOPUS:84865092901

SN - 9781467314909

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2012 International Joint Conference on Neural Networks, IJCNN 2012

T2 - 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012

Y2 - 10 June 2012 through 15 June 2012

ER -