{
  "id": 7486885,
  "title": "Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport",
  "url": "https://urgent.news/2026/09/14/learning-multimodal-one-step-flow-policy-via-value-weighted-optimal",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-14T17:10:19.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.15883v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies can naturally represent such multimodal behaviors, but learning an efficient one-step flow policy remains challenging: standard value guidance often leads to mode collapse or exploits overestimation bias in out-of-distribution regions. To address…",
  "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."
}