Initially Excited Asynchronous Reinforcement Learning Control With Monotonicity and Stability
IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2026-02 · 56 (2) · 1138-1150
DOI: 10.1109/tsmc.2025.3647521 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2026-02. Verfasst von Jiacheng Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
This article addresses the existing reinforcement learning (RL) control issues of continuous-time Markov jump systems (MJSs), including their synchronous iteration structure using nonlatest updates, nonmonotonic convergence, and requirement of initial admissible control and all-time persistent excitation (PE) condition. We propose advanced model-based and model-free RL algorithms that: 1) have asynchronous decoupled Lyapunov iteration equations to approximate the optimal control solutions using the latest updates; 2) determine the initial admissible control policy (IACP) and initial value function matrix without relying on engineering experiences; and 3) relax PE condition with a milder initial excitation (IE) condition. Rigorous theoretical analyses are provided to establish the monotonic convergence to the optimal control solution and the closed-loop stability at each iteration. Finally, the simulation and comparison results verify the proposed algorithms.
Zitieren
APA
Wu, J., Xue, W., Lewis, F. L., & Lian, B. (2026). Initially Excited Asynchronous Reinforcement Learning Control With Monotonicity and Stability. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 56(2), 1138-1150. https://doi.org/10.1109/tsmc.2025.3647521
Vancouver
Wu J, Xue W, Lewis FL, Lian B. Initially Excited Asynchronous Reinforcement Learning Control With Monotonicity and Stability. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2026;56(2):1138-1150. doi:10.1109/tsmc.2025.3647521
BibTeX
@article{Wu2026,
author = {Wu, Jiacheng and Xue, Wenqian and Lewis, Frank L. and Lian, Bosen},
title = {Initially Excited Asynchronous Reinforcement Learning Control With Monotonicity and Stability},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
year = {2026},
volume = {56},
number = {2},
pages = {1138--1150},
doi = {10.1109/tsmc.2025.3647521}
}
EUVIMED