{
  "id": 6369508,
  "title": "Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing",
  "url": "https://urgent.news/2026/09/06/second-order-smooth-planning-with-optimal-transport-bellman-smoothing",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-06T08:58:57.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.06484v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible. SmoothCruiser achieves problem-independent complexity $\\widetilde O(\\varepsilon^{-4})$ by exploiting the smoothness of the entropy-regularized Bellman backup, but its estimator is only first-order. We show that the sample-complexity exponent of SmoothCruiser-type planners is governed…",
  "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."
}