{
  "id": 11598,
  "url": "https://arxiv.org/abs/2607.15142v1",
  "title": "Concept-Guided Spatial Regularization for World Models in Atari Pong",
  "summary": "World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After reproducing their training pipelines and matching the reported agent performance, we freeze the learned world models and evaluate them with a closed-loop rollout diagnostic: a policy trained separately f",
  "authors": "Yukuan Lu, Zaishuo Xia, Weyl Lu, Yubei Chen",
  "category": "research",
  "topics": "regulation,healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-16T15:46:44.000Z",
  "fetched_at": "2026-07-18T05:10:55.931Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/11598",
  "original_url": "https://arxiv.org/abs/2607.15142v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}