{
  "id": 14385231,
  "title": "Fast Rates for Offline Q-Learning with KL Regularization",
  "url": "https://urgent.news/2026/10/13/fast-rates-for-offline-q-learning-with-kl-regularization",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T17:56:27.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.18839v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "This paper investigates offline Q-learning for finite-horizon Markov decision processes with Kullback-Leibler (KL) regularization. Recent studies have shown that KL regularization can yield fast rates in offline decision-making problems. However, it remains unclear whether Q-learning, which adopts incremental stochastic approximation updates, can achieve such fast rates in the offline setting. We…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}