{
  "abstract": "We develop a structured continuous-time q-learning framework for finite-horizon investment and optimal stopping under jump-diffusion dynamics with unknown parameters. A penalty approximation transforms the Hamilton-Jacobi-Bellman variational inequality into an HJB equation with a binary control for the stopping penalty. An auxiliary state incorporates the resulting control-dependent discount factor into a Markovian formulation. We randomize controls on the mixed action space and introduce Shannon entropy regularization, establishing policy improvement and martingale characterizations of the continuous-time q-function. These results motivate a structured q-learning algorithm that constructs the q-function from the penalty HJB equation and jointly learns the value function and unknown generator parameters from sample paths. We apply the method to portfolio choice with optimal stopping in a simulation study. We further conduct a two-asset empirical study, evaluating learned strategies on bootstrap paths from held-out test returns versus an MLE-finite difference benchmark.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.07362",
  "author_total": 2,
  "authors": [
    {
      "name": "Tingting Zhang"
    },
    {
      "name": "Can Yang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0ads7j8xx4mke.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.07362",
  "fulltext_url": null,
  "id": "0ads7j8xx4mke",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.07362",
  "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"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.07362",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0ads7j8xx4mke.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:34Z",
      "native_id": "2611.07362",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.07362"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Continuous-time q-Learning for Finite-Horizon Portfolio Choice with Optimal Stopping in Jump-Diffusion Markets",
  "title_text": "Continuous-time q-Learning for Finite-Horizon Portfolio Choice with Optimal Stopping in Jump-Diffusion Markets",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:47Z",
  "url": "https://research.draconitic.com/paper/0ads7j8xx4mke",
  "venue": "arXiv",
  "versions": []
}