{
  "url": "https://appliedfrontier.nl/en/research/signal-4fa6bb68da993aa6/",
  "title": "Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy Evaluation",
  "published": "2026-10-29",
  "excerpt": "Reinforcement learning (RL) is increasingly used to train robust, adaptable systems across healthcare, e-commerce, and robotics. In these settings, legal, ethical, or logistical concerns may",
  "content_sha256": "4a31dd3000b1d0033a843f135a64ab00e61e8d016059033159b1eb7bcc1dc4bc",
  "extracted_chars": 999,
  "artifact_links": [
    "https://arxiv.org/abs/2610.40056"
  ],
  "arxiv_id": "2610.40056",
  "extraction_scope": "preprint_abstract_metadata",
  "full_text_available": false,
  "id": "signal-4fa6bb68da993aa6",
  "org": "Research community",
  "topic": "Evaluation & safety",
  "source_kind": "preprint",
  "status": "unreviewed-source-report",
  "analysis_method": "deterministic_research_triage_v2",
  "novelty_verified": false,
  "proof_checked": false,
  "peer_review_verified": false,
  "matched_terms": [
    "Evaluation & safety"
  ],
  "checked_at": "2026-10-31T19:32:55+00:00",
  "first_seen": "2026-10-31T19:32:55+00:00",
  "source_hash": "2060832116d820d908dd5712b9bff6317a7e74235ef58b79bc1cf778ecd230d7",
  "source_url": "https://arxiv.org/abs/2610.40056",
  "language": "en",
  "indexing": "noindex_until_editorially_enriched"
}