Optimal Control of Two-Dimensional Roesser Model: Solution Based on Reinforcement Learning
IEEE Transactions on Automatic Control · 2024-08 · 69 (8) · 5424-5430
DOI: 10.1109/tac.2024.3357743 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2024-08. Verfasst von Linwei Ye und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This article addresses the infinite-region linear quadratic regulation problem of the discrete two-dimensional (2-D) Roesser model, drawing inspiration from reinforcement learning principles. It introduces a novel proof establishing that expressing the optimal control law in 2-D through state feedback is unattainable. Subsequently, a policy iteration framework is proposed to derive suboptimal state feedback, followed by an exploration of the true optimal policy through value iteration. The efficacy of these methodologies is demonstrated via two numerical examples, enhancing the practical understanding of these innovative approaches.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Ye, L., Zhao, Z., & Liu, F. (2024). Optimal Control of Two-Dimensional Roesser Model: Solution Based on Reinforcement Learning. IEEE Transactions on Automatic Control, 69(8), 5424-5430. https://doi.org/10.1109/tac.2024.3357743
Vancouver
Ye L, Zhao Z, Liu F. Optimal Control of Two-Dimensional Roesser Model: Solution Based on Reinforcement Learning. IEEE Transactions on Automatic Control. 2024;69(8):5424-5430. doi:10.1109/tac.2024.3357743
BibTeX
@article{Ye2024,
author = {Ye, Linwei and Zhao, Zhonggai and Liu, Fei},
title = {Optimal Control of Two-Dimensional Roesser Model: Solution Based on Reinforcement Learning},
journal = {IEEE Transactions on Automatic Control},
year = {2024},
volume = {69},
number = {8},
pages = {5424--5430},
doi = {10.1109/tac.2024.3357743}
}
EUVIMED