Metraipolis › archive › dc_cd3079cf9872

Policy Iteration for Domain Randomized Linear Quadratic Systems — arXiv:2609.04794

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04794
License (as archived)
CC0-1.0
Archived
2026-10-16T23:11:28.708Z
SHA-256 of the archived text
99c14d4aa628eb26627017373924a49d998c7be604a5e27eebeec193cdba9a46
Stable URL of this page
https://metraipolis.com/documento/dc_cd3079cf9872

How to cite

Policy Iteration for Domain Randomized Linear Quadratic Systems — arXiv:2609.04794 — arXiv (en), https://arxiv.org/abs/2609.04794 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd3079cf9872 (Metraipolis archive dc_cd3079cf9872, sha256 99c14d4aa628eb26627017373924a49d998c7be604a5e27eebeec193cdba9a46)
BibTeX
@misc{dccd3079cf9872,
  title = {Policy Iteration for Domain Randomized Linear Quadratic Systems — arXiv:2609.04794},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04794},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd3079cf9872; sha256 99c14d4aa628eb26627017373924a49d998c7be604a5e27eebeec193cdba9a46},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04794. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this work, we study policy optimization under domain randomization for linear quadratic control, focusing on learning a single state-feedback controller that minimizes the average cost across systems with uncertain dynamics. We propose a policy iteration algorithm with a step-size rule that preserves stability across all sampled systems at each iteration. We show that the method yields monotonic improvement of the sample-average objective and that a stabilizing step size always exists. Under standard smoothness assumptions, the iterates converge subsequentially to stationary points, and under a gradient-dominance condition, we obtain a global linear convergence rate.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-07 in math.OC).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.04794 — 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 2026-10-16T22:51:59.420Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).