Metraipolis › archive › dc_372b72720fe7

Data-Driven Policy Iteration Without an Initial Stabilizing Policy: A Finite-Horizon Bootstrap Method — arXiv:2609.17191

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17191
License (as archived)
CC0-1.0
Archived
2026-10-15T22:39:26.144Z
SHA-256 of the archived text
5a1c7c0dc52695a3043ace729217b1a2587827cea67513a7033d9f22ab53c6be
Stable URL of this page
https://metraipolis.com/documento/dc_372b72720fe7

How to cite

Data-Driven Policy Iteration Without an Initial Stabilizing Policy: A Finite-Horizon Bootstrap Method — arXiv:2609.17191 — arXiv (en), https://arxiv.org/abs/2609.17191 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_372b72720fe7 (Metraipolis archive dc_372b72720fe7, sha256 5a1c7c0dc52695a3043ace729217b1a2587827cea67513a7033d9f22ab53c6be)
BibTeX
@misc{dc372b72720fe7,
  title = {Data-Driven Policy Iteration Without an Initial Stabilizing Policy: A Finite-Horizon Bootstrap Method — arXiv:2609.17191},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17191},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_372b72720fe7; sha256 5a1c7c0dc52695a3043ace729217b1a2587827cea67513a7033d9f22ab53c6be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17191. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This article investigates data-driven policy iteration (PI) for continuous-time linear systems without requiring an initially stabilizing policy. Standard infinite-horizon PI is not self-starting because its policy-evaluation step is well posed only when the feedback gain is stabilizing. However, verifying this property is difficult when the system matrices are unknown. To remove this requirement, we develop a finite-horizon bootstrap method. The key idea is to perform policy evaluation over a compact interval for a shifted system, where the evaluation equation is well defined for arbitrary bounded time-varying policies. We show that, for a sufficiently long horizon, the initial-time optimal gain of the shifted finite-horizon problem, when applied as a constant feedback gain, achieves a prescribed stability margin for the original system. We then derive a data-driven implementation from an off-policy identity evaluated along trajectories of the original plant. We use basis-function approximations to reconstruct the finite-horizon value matrix and policy, and we characterize the resulting error through a perturbed policy-improvement recursion. A data-driven Lyapunov certificate is further introduced to verify admissibility of the candidate gain before it is used to initialize infinite-horizon PI. Numerical studies of a batch reactor and a two-mass-spring system demonstrate the effectiveness of the proposed bootstrap method.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-16 in eess.SY).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.17191 — 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 2026-10-15T22:15:42.179Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).