{
  "id": 10589384,
  "title": "Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic",
  "url": "https://urgent.news/2026/09/26/rank-collapse-is-recoverable-growing-q-is-not-out-of-sample-early",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-26T17:46:16.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.32819v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Raising the update-to-data (UTD) ratio breaks off-policy critics in two ways grouped as \"plasticity loss\": collapsing representations and growing value magnitude $|Q|$. We separate them in Soft Actor-Critic (SAC) with scaled critics (width 2048, no normalization). Collapse is survivable: at UTD ratio 16, HalfCheetah critics with most units dormant keep learning, and the training guard, which…",
  "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."
}