Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems

Zhiyi Gao; Gaojie Wang; Zhuoyue Song

doi:10.1109/FASTA70174.2026.11549022

Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems

Zhiyi Gao
, Gaojie Wang
, Zhuoyue Song^*

^*Corresponding author for this work

Beijing Institute of Technology
Beijing Institute of Technology

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

Abstract

This paper investigates the reinforcement learning (RL)-based prescribed-time optimal tracking control problem for a class of uncertain nonlinear strict-feedback systems. To circumvent the 'explosion of complexity' inherent in recursive backstepping, the High-Order Fully Actuated (HOFA) system approach is employed to reformulate the dynamics. Based on the actor-critic framework, this work integrates the prescribed-time adjustment function into the neural network (NN) update laws, which synchronizes the prescribed-time convergence of both the tracking error and the network weights under a unified Lyapunov framework, thus ensuring the stability of the entire system within a prescribed time. A complete and rigorous proof is presented via Lyapunov theory. Finally, a numerical example is given to show the effectiveness of the proposed results.

Original language	English
Title of host publication	Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1812-1817
Number of pages	6
ISBN (Electronic)	9798319547323
DOIs	https://doi.org/10.1109/FASTA70174.2026.11549022
Publication status	Published - 2026
Externally published	Yes
Event	5th Conference on Fully Actuated System Theory and Applications, FASTA 2026 - Qinhuangdao, China Duration: 22 May 2026 → 24 May 2026

Publication series

Name	Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026

Conference

Conference	5th Conference on Fully Actuated System Theory and Applications, FASTA 2026
Country/Territory	China
City	Qinhuangdao
Period	22/05/26 → 24/05/26

Keywords

High-Order Fully Actuated Systems Approach
Optimal Control
Prescribed-Time
Reinforcement Learning

Access to Document

10.1109/FASTA70174.2026.11549022

Cite this

Gao, Z., Wang, G., & Song, Z. (2026). Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems. In Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026 (pp. 1812-1817). (Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FASTA70174.2026.11549022

Gao, Zhiyi ; Wang, Gaojie ; Song, Zhuoyue. / Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems. Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026. Institute of Electrical and Electronics Engineers Inc., 2026. pp. 1812-1817 (Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026).

@inproceedings{62c5751925874702869b6e395a764af2,

title = "Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems",

abstract = "This paper investigates the reinforcement learning (RL)-based prescribed-time optimal tracking control problem for a class of uncertain nonlinear strict-feedback systems. To circumvent the 'explosion of complexity' inherent in recursive backstepping, the High-Order Fully Actuated (HOFA) system approach is employed to reformulate the dynamics. Based on the actor-critic framework, this work integrates the prescribed-time adjustment function into the neural network (NN) update laws, which synchronizes the prescribed-time convergence of both the tracking error and the network weights under a unified Lyapunov framework, thus ensuring the stability of the entire system within a prescribed time. A complete and rigorous proof is presented via Lyapunov theory. Finally, a numerical example is given to show the effectiveness of the proposed results.",

keywords = "High-Order Fully Actuated Systems Approach, Optimal Control, Prescribed-Time, Reinforcement Learning",

author = "Zhiyi Gao and Gaojie Wang and Zhuoyue Song",

note = "Publisher Copyright: {\textcopyright} 2026 IEEE.; 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026 ; Conference date: 22-05-2026 Through 24-05-2026",

year = "2026",

doi = "10.1109/FASTA70174.2026.11549022",

language = "English",

series = "Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1812--1817",

booktitle = "Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026",

address = "United States",

}

Gao, Z, Wang, G & Song, Z 2026, Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems. in Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026. Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026, Institute of Electrical and Electronics Engineers Inc., pp. 1812-1817, 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026, Qinhuangdao, China, 22/05/26. https://doi.org/10.1109/FASTA70174.2026.11549022

Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems. / Gao, Zhiyi; Wang, Gaojie; Song, Zhuoyue.
Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026. Institute of Electrical and Electronics Engineers Inc., 2026. p. 1812-1817 (Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026).

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

TY - GEN

T1 - Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems

AU - Gao, Zhiyi

AU - Wang, Gaojie

AU - Song, Zhuoyue

PY - 2026

Y1 - 2026

N2 - This paper investigates the reinforcement learning (RL)-based prescribed-time optimal tracking control problem for a class of uncertain nonlinear strict-feedback systems. To circumvent the 'explosion of complexity' inherent in recursive backstepping, the High-Order Fully Actuated (HOFA) system approach is employed to reformulate the dynamics. Based on the actor-critic framework, this work integrates the prescribed-time adjustment function into the neural network (NN) update laws, which synchronizes the prescribed-time convergence of both the tracking error and the network weights under a unified Lyapunov framework, thus ensuring the stability of the entire system within a prescribed time. A complete and rigorous proof is presented via Lyapunov theory. Finally, a numerical example is given to show the effectiveness of the proposed results.

AB - This paper investigates the reinforcement learning (RL)-based prescribed-time optimal tracking control problem for a class of uncertain nonlinear strict-feedback systems. To circumvent the 'explosion of complexity' inherent in recursive backstepping, the High-Order Fully Actuated (HOFA) system approach is employed to reformulate the dynamics. Based on the actor-critic framework, this work integrates the prescribed-time adjustment function into the neural network (NN) update laws, which synchronizes the prescribed-time convergence of both the tracking error and the network weights under a unified Lyapunov framework, thus ensuring the stability of the entire system within a prescribed time. A complete and rigorous proof is presented via Lyapunov theory. Finally, a numerical example is given to show the effectiveness of the proposed results.

KW - High-Order Fully Actuated Systems Approach

KW - Optimal Control

KW - Prescribed-Time

KW - Reinforcement Learning

UR - https://www.scopus.com/pages/publications/105043539469

U2 - 10.1109/FASTA70174.2026.11549022

DO - 10.1109/FASTA70174.2026.11549022

M3 - Conference contribution

AN - SCOPUS:105043539469

T3 - Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026

SP - 1812

EP - 1817

BT - Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026

Y2 - 22 May 2026 through 24 May 2026

ER -

Gao Z, Wang G, Song Z. Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems. In Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026. Institute of Electrical and Electronics Engineers Inc. 2026. p. 1812-1817. (Proceedings of the 5th Conference on Fully Actuated System Theory and Applications, FASTA 2026). doi: 10.1109/FASTA70174.2026.11549022

Reinforcement Learning-Based Prescribed-Time Optimal Tracking Control for Uncertain Nonlinear Strict-Feedback Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this