{
  "abstract": "We study how to evaluate $K$ target policies simultaneously in stochastic contextual bandits with linear reward structure. Given a known $d$-dimensional feature map and reward-free access to policy queries, we propose PRISMA (Policy evaluation through Regularized Information Sharing and Mixture Allocation), an algorithm that estimates every target policy's value to accuracy $\\varepsilon$ with probability at least $1-δ$. The algorithm uses $\\widetilde{\\mathcal{O}}\\!\\left( \\frac{(L^2S^2+β^2)(1\\veeρ^\\star)}{\\varepsilon^2} \\cdot \\log(K) \\right)$ context draws and reward observations, where $ρ^\\star\\le d$ is an instance-dependent measure of the difficulty of designing a shared sampling distribution. Here, $L$, $S$, and $β$ bound the feature norm, reward parameter norm, and reward noise, respectively, and the suppressed factors are logarithmic in $K$, $d$, and $1/δ$. Our method combines reward-free planning, a regularized sampling design, and a single ridge regression estimator shared across all target policies. An adaptive doubling procedure selects the regularization scale without knowledge of $ρ^\\star$. The guarantees require no numerical lower bound on second-moment eigenvalues and have no explicit dependence on the cardinalities of the context and action spaces. Policy-query costs are accounted for separately, with $K$ queries per shared planning context.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.22252",
  "author_total": 3,
  "authors": [
    {
      "name": "Spyros Dragazis"
    },
    {
      "name": "Yilei Chen"
    },
    {
      "name": "Aldo Pacchiano"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a7h23vdg6sgkr.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.22252",
  "fulltext_url": null,
  "id": "a7h23vdg6sgkr",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.22252",
  "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.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7222450971",
  "pdf_url": "https://arxiv.org/pdf/2610.22252",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a7h23vdg6sgkr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:00Z",
      "native_id": "2610.22252",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.22252"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits",
  "title_text": "Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits",
  "type": "preprint",
  "updated_at": "2026-10-30T12:30:00Z",
  "url": "https://research.draconitic.com/paper/a7h23vdg6sgkr",
  "venue": "arXiv",
  "versions": []
}