Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach
SIAM Journal on Control and Optimization · 30.04.2026 · 64 (2) · 816-842
DOI: 10.1137/24m1680039 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Control and Optimization, online erschienen am 09.04.2026. Verfasst von Jin Ma und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
In this paper we investigate the convergence of the policy iteration algorithm (PIA) for a class of general continuous-time entropy-regularized stochastic control problems. In particular, instead of employing sophisticated PDE estimates for the iterative PDEs involved in the algorithm (see, e.g., Huang, Wang, and Zhou [ SIAM J. Control Optim., 63 (2025), pp. 752–777]), we shall provide a simple proof from scratch for the convergence of the PIA. Our approach builds on probabilistic representation formulae for solutions of PDEs and their derivatives. Moreover, in the finite horizon model and in the infinite horizon model with large discount factor, similar arguments lead to a superexponential rate of convergence without tear. Finally, with some extra effort we show that our approach can be extended to the diffusion control case in the one-dimensional setting, also with a superexponential rate of convergence.
Förderung
- National Science Foundation
Zitieren
APA
Ma, J., Wang, G., & Zhang, J. (2026). Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach. SIAM Journal on Control and Optimization, 64(2), 816-842. https://doi.org/10.1137/24m1680039
Vancouver
Ma J, Wang G, Zhang J. Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach. SIAM Journal on Control and Optimization. 2026;64(2):816-842. doi:10.1137/24m1680039
BibTeX
@article{Ma2026,
author = {Ma, Jin and Wang, Gaozhan and Zhang, Jianfeng},
title = {Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach},
journal = {SIAM Journal on Control and Optimization},
year = {2026},
volume = {64},
number = {2},
pages = {816--842},
doi = {10.1137/24m1680039}
}
EUVIMED