{
  "abstract": "We study the worst-case, over priors, Bayesian conditional value-at-risk (CVaR) of cumulative pseudo-regret in time-homogeneous finite-horizon episodic Markov decision processes. A high-probability guarantee for UCBVI-BF yields a prior-predictive upper bound. A lower bound follows by a three-state MDP and applying a reverse-KL inequality. For a constant number of states, the bounds have the same polynomial dependence on horizon, actions, and episodes, with a logarithmic gap in the risk level.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.28157",
  "author_total": 4,
  "authors": [
    {
      "name": "Raghav Bongole"
    },
    {
      "name": "Amirreza Zamani"
    },
    {
      "name": "Tobias J. Oechtering"
    },
    {
      "name": "Mikael Skoglund"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fs5v37p55nbcz.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.28157",
  "fulltext_url": null,
  "id": "fs5v37p55nbcz",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.28157",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7223101675",
  "pdf_url": "https://arxiv.org/pdf/2610.28157",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fs5v37p55nbcz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:08Z",
      "native_id": "2610.28157",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.28157"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Worst-Case Bayesian CVaR Regret Bounds for Episodic Markov Decision Processes",
  "title_text": "Worst-Case Bayesian CVaR Regret Bounds for Episodic Markov Decision Processes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:08Z",
  "url": "https://research.draconitic.com/paper/fs5v37p55nbcz",
  "venue": "arXiv",
  "versions": []
}