{
  "abstract": "We develop simulation-based policy iteration for continuous-time portfolio choice with predictable returns and convex constraints. Each outer step re-evaluates a fixed-latent open-loop backpropagation-through-time (OL-BPTT) adjoint after deployment and solves the constrained update. Shifted-adjoint cancellation controls the adjoint--HJB Hamiltonian-gradient discrepancy by the policy-improvement residual. For CRRA portfolios, exact HJB policy iteration identifies the optimal reduced value factor, while population OL-BPTT iteration converges globally when the adjoint update is directionally improving and approximate stationarity is asymptotically HJB-compatible. A theorem-matched occupation audit yields maximal $95\\%$ upper endpoints of $0.066$ for the primitive directional ratio and $0.074$ for a stronger norm-relative ratio, both against the half-step threshold $0.75$. In the high-precision $50$--$50$ occupancy/broad-anchor design of a three-factor, fifty-asset benchmark, current-policy re-evaluation outperforms matched pooled refinement under the on-policy and broad evaluation laws.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.17808",
  "author_total": 3,
  "authors": [
    {
      "name": "Jeonggyu Huh"
    },
    {
      "name": "Yeoneung Kim"
    },
    {
      "name": "Seungwon Jeong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7n0wnqzgwa3te.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.17808",
  "fulltext_url": null,
  "id": "7n0wnqzgwa3te",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.17808",
  "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",
      "math.OC"
    ],
    [
      "arxiv",
      "q-fin.CP"
    ],
    [
      "arxiv",
      "q-fin.PM"
    ],
    [
      "openalex",
      "2003|Stochastic processes and financial applications"
    ]
  ],
  "openalex": "W7203782835",
  "pdf_url": "https://arxiv.org/pdf/2608.17808",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7n0wnqzgwa3te.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:58Z",
      "native_id": "2608.17808",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.17808"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Self-Consistent Adjoint Policy Iteration for Constrained Dynamic Portfolio Choice",
  "title_text": "Self-Consistent Adjoint Policy Iteration for Constrained Dynamic Portfolio Choice",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:58Z",
  "url": "https://research.draconitic.com/paper/7n0wnqzgwa3te",
  "venue": "arXiv",
  "versions": []
}