{
  "abstract": "Closed-loop planning accounts for future observation-dependent actions but can be expensive to repeat at deployment. Bellman-gradient (BG) refinement differentiates conditional rollouts through an existing actor, corrects the current action, and stores the result in an executable policy. A backward sweep reuses deployed future feedback; full-horizon rollouts in an identified Gaussian belief model need no learned value critic. A nonlinear error recursion links quadratic continuation error, local correction, and policy storage. A controlled non-LQG example exhibits second-order policy accuracy with consistent storage, while ideal affine LQG admits exact backward recovery. In nonquadratic thrust, BG reduces actor cost by 2.47-3.20% and remains within 0.13-0.53% of the tested feedback MPC; original policies execute in 5-6 microseconds in a seed-0 native audit. With matched storage, BG attains competitive plant costs at about one ninth (arm) and one sixtieth (docking) of feedback-teacher-plus-student construction time on one GPU, excluding shared learning and node preparation. Richer common maps substantially narrow some student-BG gaps. These results expose the roles of learned feedback, local correction, and storage in executable control.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.35012",
  "author_total": 1,
  "authors": [
    {
      "name": "Jeonggyu Huh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/aveq354dtqn0e.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.35012",
  "fulltext_url": null,
  "id": "aveq354dtqn0e",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.35012",
  "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",
      "1702|Reinforcement Learning in Robotics"
    ]
  ],
  "openalex": "W7214753093",
  "pdf_url": "https://arxiv.org/pdf/2609.35012",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/aveq354dtqn0e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:17Z",
      "native_id": "2609.35012",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.35012"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Amortized Feedback Planning: Turning Model-Based Rollouts into Executable Policies",
  "title_text": "Amortized Feedback Planning: Turning Model-Based Rollouts into Executable Policies",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:17Z",
  "url": "https://research.draconitic.com/paper/aveq354dtqn0e",
  "venue": "arXiv",
  "versions": []
}