{
  "abstract": null,
  "abstract_shown": false,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.20347",
  "author_total": 4,
  "authors": [
    {
      "name": "Kintan Saha"
    },
    {
      "name": "Ahana Deb"
    },
    {
      "name": "Anders Jonsson"
    },
    {
      "name": "Debabrota Basu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dtsjfng4cqk4j.bib",
  "cited_by": 0,
  "doi": null,
  "fulltext_url": null,
  "id": "dtsjfng4cqk4j",
  "issns": [],
  "landing_url": "https://inria.hal.science/hal-05828957v1",
  "language": "en",
  "licence": "unknown",
  "licence_label": "Licence not stated",
  "licence_source": "unknown",
  "licence_url": null,
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.stat"
    ],
    [
      "hal",
      "1.info.info-ai"
    ],
    [
      "hal",
      "1.info.info-lg"
    ],
    [
      "hal",
      "1.stat.co"
    ],
    [
      "hal",
      "1.stat.ml"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dtsjfng4cqk4j.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:00Z",
      "native_id": "hal-05828957",
      "source": "hal",
      "url": "https://inria.hal.science/hal-05828957v1"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "hal:0.stat",
      "subfield": "statistics"
    }
  ],
  "title": "Non-asymptotic Convergence of Average-reward Q-learning with Options",
  "title_text": "Non-asymptotic Convergence of Average-reward Q-learning with Options",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:00Z",
  "url": "https://research.draconitic.com/paper/dtsjfng4cqk4j",
  "venue": "HAL",
  "versions": []
}