Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a complete answer to the longstanding unanswered question of what value iteration (VI) is for continuous-time, continuous-state-action space nonlinear systems. Based on this proposed VI, we develop a new data-driven adaptive optimal control methodology for unknown nonlinear systems. As compared with the existing literature of adaptive dynamic programming (ADP) for continuous-time systems which often uses policy iteration (PI), an initial admissible control policy is no longer required. By means of the obtained result, a non-model-based adaptive optimal control design is given. The effectiveness of the proposed methodology is also illustrated by an example.

Original languageEnglish (US)
Title of host publication2016 IEEE 55th Conference on Decision and Control, CDC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3375-3380
Number of pages6
ISBN (Electronic)9781509018376
DOIs
StatePublished - Dec 27 2016
Event55th IEEE Conference on Decision and Control, CDC 2016 - Las Vegas, United States
Duration: Dec 12 2016Dec 14 2016

Other

Other55th IEEE Conference on Decision and Control, CDC 2016
CountryUnited States
CityLas Vegas
Period12/12/1612/14/16

Fingerprint

Value Iteration
Adaptive Dynamics
Dynamic programming
Adaptive Control
Dynamic Programming
Nonlinear systems
Optimal Control
Nonlinear Systems
Policy Iteration
Methodology
Continuous-time Systems
Control Policy
Data-driven
Control Design
Continuous Time
Continuous time systems
Unknown
Adaptive dynamics
Continuous time
Optimal control

ASJC Scopus subject areas

  • Artificial Intelligence
  • Decision Sciences (miscellaneous)
  • Control and Optimization

Cite this

Bian, T., & Jiang, Z-P. (2016). Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems. In 2016 IEEE 55th Conference on Decision and Control, CDC 2016 (pp. 3375-3380). [7798777] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CDC.2016.7798777

Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems. / Bian, Tao; Jiang, Zhong-Ping.

2016 IEEE 55th Conference on Decision and Control, CDC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 3375-3380 7798777.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bian, T & Jiang, Z-P 2016, Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems. in 2016 IEEE 55th Conference on Decision and Control, CDC 2016., 7798777, Institute of Electrical and Electronics Engineers Inc., pp. 3375-3380, 55th IEEE Conference on Decision and Control, CDC 2016, Las Vegas, United States, 12/12/16. https://doi.org/10.1109/CDC.2016.7798777
Bian T, Jiang Z-P. Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems. In 2016 IEEE 55th Conference on Decision and Control, CDC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 3375-3380. 7798777 https://doi.org/10.1109/CDC.2016.7798777
Bian, Tao ; Jiang, Zhong-Ping. / Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems. 2016 IEEE 55th Conference on Decision and Control, CDC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 3375-3380
@inproceedings{43e3143f601c4efcab6e0d7f4ed03784,
title = "Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems",
abstract = "This paper presents a complete answer to the longstanding unanswered question of what value iteration (VI) is for continuous-time, continuous-state-action space nonlinear systems. Based on this proposed VI, we develop a new data-driven adaptive optimal control methodology for unknown nonlinear systems. As compared with the existing literature of adaptive dynamic programming (ADP) for continuous-time systems which often uses policy iteration (PI), an initial admissible control policy is no longer required. By means of the obtained result, a non-model-based adaptive optimal control design is given. The effectiveness of the proposed methodology is also illustrated by an example.",
author = "Tao Bian and Zhong-Ping Jiang",
year = "2016",
month = "12",
day = "27",
doi = "10.1109/CDC.2016.7798777",
language = "English (US)",
pages = "3375--3380",
booktitle = "2016 IEEE 55th Conference on Decision and Control, CDC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Value iteration, adaptive dynamic programming, and optimal control of nonlinear systems

AU - Bian, Tao

AU - Jiang, Zhong-Ping

PY - 2016/12/27

Y1 - 2016/12/27

N2 - This paper presents a complete answer to the longstanding unanswered question of what value iteration (VI) is for continuous-time, continuous-state-action space nonlinear systems. Based on this proposed VI, we develop a new data-driven adaptive optimal control methodology for unknown nonlinear systems. As compared with the existing literature of adaptive dynamic programming (ADP) for continuous-time systems which often uses policy iteration (PI), an initial admissible control policy is no longer required. By means of the obtained result, a non-model-based adaptive optimal control design is given. The effectiveness of the proposed methodology is also illustrated by an example.

AB - This paper presents a complete answer to the longstanding unanswered question of what value iteration (VI) is for continuous-time, continuous-state-action space nonlinear systems. Based on this proposed VI, we develop a new data-driven adaptive optimal control methodology for unknown nonlinear systems. As compared with the existing literature of adaptive dynamic programming (ADP) for continuous-time systems which often uses policy iteration (PI), an initial admissible control policy is no longer required. By means of the obtained result, a non-model-based adaptive optimal control design is given. The effectiveness of the proposed methodology is also illustrated by an example.

UR - http://www.scopus.com/inward/record.url?scp=85010764224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010764224&partnerID=8YFLogxK

U2 - 10.1109/CDC.2016.7798777

DO - 10.1109/CDC.2016.7798777

M3 - Conference contribution

AN - SCOPUS:85010764224

SP - 3375

EP - 3380

BT - 2016 IEEE 55th Conference on Decision and Control, CDC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -