{
  "abstract": "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.04794",
  "author_total": 2,
  "authors": [
    {
      "name": "Abbas Pasdar"
    },
    {
      "name": "Farnaz Adib Yaghmaie"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cq4yv0jqbz46f.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.04794",
  "fulltext_url": null,
  "id": "cq4yv0jqbz46f",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.04794",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.SY"
    ],
    [
      "arxiv",
      "eess.SY"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1703|Adaptive Dynamic Programming Control"
    ]
  ],
  "openalex": "W7211868061",
  "pdf_url": "https://arxiv.org/pdf/2609.04794",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cq4yv0jqbz46f.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:15Z",
      "native_id": "2609.04794",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.04794"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Policy Iteration for Domain Randomized Linear Quadratic Systems",
  "title_text": "Policy Iteration for Domain Randomized Linear Quadratic Systems",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:15Z",
  "url": "https://research.draconitic.com/paper/cq4yv0jqbz46f",
  "venue": "arXiv",
  "versions": []
}