Policy Iteration Reinforcement Learning Method for Continuous-Time Linear–Quadratic Mean-Field Control Problems
IEEE Transactions on Automatic Control · 2025-04 · 70 (4) · 2690-2697
DOI: 10.1109/tac.2024.3494656 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2025-04. Verfasst von Na Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Consulting and Research Project of China Engineering Science and Technology Development Strategy Shandong Research Institute, International Cooperation Research Platform of Shandong University of Finance and Economics.
Abstract (Originalsprache)
In this article, we employ a policy iteration reinforcement learning (RL) method to study continuous-time linear–quadratic mean-field control problems in infinite horizon. The drift and diffusion terms in the dynamics involve the states, the controls, and their conditional expectations. We investigate the stabilizability and convergence of the RL algorithm using a Lyapunov recursion. Instead of solving a pair of coupled Riccati equations, the RL technique focuses on strengthening an auxiliary function and the cost functional as the objective functions and updating the new policy to compute the optimal control via state trajectories. A numerical example sheds light on the established theoretical results.
Förderung
- National Natural Science Foundation of China
- Consulting and Research Project of China Engineering Science and Technology Development Strategy Shandong Research Institute
- International Cooperation Research Platform of Shandong University of Finance and Economics
- Research Grants Council of Hong Kong
- Hong Kong RGC
- PolyU-SDU Joint Research Center on Financial Mathematics
- CAS AMSS-PolyU Joint Laboratory of Applied Mathematics
- Research Centre for Quantitative Finance
Zitieren
APA
Li, N., Li, X., & Xu, Z. Q. (2025). Policy Iteration Reinforcement Learning Method for Continuous-Time Linear–Quadratic Mean-Field Control Problems. IEEE Transactions on Automatic Control, 70(4), 2690-2697. https://doi.org/10.1109/tac.2024.3494656
Vancouver
Li N, Li X, Xu ZQ. Policy Iteration Reinforcement Learning Method for Continuous-Time Linear–Quadratic Mean-Field Control Problems. IEEE Transactions on Automatic Control. 2025;70(4):2690-2697. doi:10.1109/tac.2024.3494656
BibTeX
@article{Li2025,
author = {Li, Na and Li, Xun and Xu, Zuo Quan},
title = {Policy Iteration Reinforcement Learning Method for Continuous-Time Linear–Quadratic Mean-Field Control Problems},
journal = {IEEE Transactions on Automatic Control},
year = {2025},
volume = {70},
number = {4},
pages = {2690--2697},
doi = {10.1109/tac.2024.3494656}
}
EUVIMED