Metraipolis › archive › dc_0dea4cb17c67

On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization — arXiv:2611.02340

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02340
License (as archived)
CC0-1.0
Archived
2026-11-03T18:40:43.197Z
SHA-256 of the archived text
d6ec9e49bdf2ffef3059303ffe925556206ed28114e7fca15adeac91a5886bf1
Stable URL of this page
https://metraipolis.com/documento/dc_0dea4cb17c67

How to cite

On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization — arXiv:2611.02340 — arXiv (en), https://arxiv.org/abs/2611.02340 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0dea4cb17c67 (Metraipolis archive dc_0dea4cb17c67, sha256 d6ec9e49bdf2ffef3059303ffe925556206ed28114e7fca15adeac91a5886bf1)
BibTeX
@misc{dc0dea4cb17c67,
  title = {On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization — arXiv:2611.02340},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02340},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0dea4cb17c67; sha256 d6ec9e49bdf2ffef3059303ffe925556206ed28114e7fca15adeac91a5886bf1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02340. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning to stabilize an unknown continuous-time stochastic linear system is a central problem in control theory and reinforcement learning. This paper numerically studies data-driven identification of such systems with possibly unstable dynamics for the purpose of stabilization. We present a method that learns a stabilizing gain from observed trajectories, and examine how the failure probability, namely the probability that the learned gain does not stabilize the system, depends on the amount of data, dimension, noise intensity, excitation, and controllability. Numerical experiments on an unstable batch-reactor benchmark show that the squared identification error decays inversely with the aggregate observation time, that is, the combined length of all trajectories, while the failure probability decays exponentially in the same quantity. Hence, despite instability, a single long trajectory can achieve similar stabilization performance to that of many short trajectories of the same total length. We also observe \emph{signal saturation}: stronger excitation improves stabilization only logarithmically with the excitation strength. Finally, we show experimentally that accurate identification of the full dynamics is \emph{not} necessary for successful stabilization.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02340 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.766Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).