{
  "id": 12513422,
  "title": "Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA",
  "url": "https://urgent.news/2026/10/06/learning-in-dreams-winning-in-reality-a-continuous-dyna-loop-for-a",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-06T09:26:48.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.08033v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look. We judge one from the outside. We learn a structured, multi-agent world model of a complete ten-hero MOBA (206 units, every hero acting every tick, games of up to 6,000 ticks), train a policy only inside it with 1,400-tick free-running imagined…",
  "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."
}