{
  "id": 3038,
  "url": "https://arxiv.org/abs/2607.11607v1",
  "title": "Auditing the Risk Claims of Distributional Reinforcement Learning",
  "summary": "Distributional reinforcement learning agents learn full return distributions that are increasingly read at face value: for interpretability, risk-sensitive control, and safety monitoring. We ask a question theory anticipates but that has not been measured directly: are the risk claims of a trained distributional agent true? Our audit combines a decision-relevant screening metric (the excess Wasserstein gap between the top two actions, which equals the mass by which first-order stochastic dominan",
  "authors": "Hari Prasad",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-13T14:30:01.000Z",
  "fetched_at": "2026-07-14T16:11:46.979Z",
  "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/3038",
  "original_url": "https://arxiv.org/abs/2607.11607v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}