{
  "abstract": "Randomized experiments are the standard for measuring causal effects that guide decisions, but are costly. Simulators calibrated to historical data offer a cheaper alternative, but their policies can become suboptimal under drift, a change in dynamics after calibration. We study if, when, and how to collect data for recalibrating the simulator. We consider a system with multiple units running in parallel and managed by a single operator. The real-world system is a partially observed process with a latent variable, while the simulator models it as a fully observed Markovian process, and thus is misspecified. Two data collection strategies exploit the current policy: (i) never recalibrating and (ii) recalibrating from on-policy data (passive adaptation). Two others collect off-policy data by trying actions outside the current policy: (iii) continuous exploration across all units and (iv) randomized experimentation on a sample of units over a predefined window. We investigate these strategies theoretically and in a vending-machine simulation. Experiments can improve on passive adaptation when drift is invisible in on-policy data or recalibration lags behind continuing drift. Experimentation is preferable to exploration when trying a worse action is expensive and the dynamics may not have changed.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.21458",
  "author_total": 6,
  "authors": [
    {
      "name": "Harsh Parikh"
    },
    {
      "name": "Gabriel Levin-Konigsberg"
    },
    {
      "name": "Sohrab Andaz"
    },
    {
      "name": "Akhil Bagaria"
    },
    {
      "name": "Dominique Perrault-Joncas"
    },
    {
      "name": "Alexander Volfovsky"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/03wgb37v71eve.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.21458",
  "fulltext_url": null,
  "id": "03wgb37v71eve",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.21458",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "openalex",
      "1702|Reinforcement Learning in Robotics"
    ]
  ],
  "openalex": "W7161976347",
  "pdf_url": "https://arxiv.org/pdf/2605.21458",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/03wgb37v71eve.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:43Z",
      "native_id": "2605.21458",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.21458"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "Exploration and Experimentation with a Misspecified Simulator",
  "title_text": "Exploration and Experimentation with a Misspecified Simulator",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:38Z",
  "url": "https://research.draconitic.com/paper/03wgb37v71eve",
  "venue": "arXiv",
  "versions": []
}