Koopman Spectrum RL for Bifurcation Control: Data-Driven Policy Optimization in Spectral Subspaces
Mathematics · 26.05.2026 · 14 (11) · 1847
DOI: 10.3390/math14111847 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 26.05.2026. Verfasst von Dipesh und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper presents a reinforcement learning (RL) framework based on the Koopman operator for high-dimensional nonlinear control. By leveraging nonlinear eigenvalue dynamics, the approach enables scalable and efficient policy optimization. We examined the challenge of controlling complex systems by embedding high-dimensional states xt∈Rn into a Koopman-invariant subspace ϕx∈Rm, where evolution becomes linear under the Koopman operator K. By spectrally decomposing K=UΛU−1, the eigenvalue dynamics are obtained, and K is reconstructed iteratively via dominant eigenpairs vi,wi. A policy network πa|s selects actions ut, while a value function Vs, expressed in Koopman eigenfunction coordinates, guides gradient-based policy updates. The framework integrates spectral stability constraints (ρX
Zitieren
APA
Dipesh, Dhatterwal, J. S., & Ayna, H. O. (2026). Koopman Spectrum RL for Bifurcation Control: Data-Driven Policy Optimization in Spectral Subspaces. Mathematics, 14(11), 1847. https://doi.org/10.3390/math14111847
Vancouver
Dipesh, Dhatterwal JS, Ayna HO. Koopman Spectrum RL for Bifurcation Control: Data-Driven Policy Optimization in Spectral Subspaces. Mathematics. 2026;14(11):1847. doi:10.3390/math14111847
BibTeX
@article{Dipesh2026,
author = {Dipesh and Dhatterwal, Jagjit Singh and Ayna, Hacer Ozden},
title = {Koopman Spectrum RL for Bifurcation Control: Data-Driven Policy Optimization in Spectral Subspaces},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {11},
pages = {1847},
doi = {10.3390/math14111847}
}
EUVIMED