{
  "id": 16089,
  "url": "https://arxiv.org/abs/2608.02509v1",
  "title": "Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies",
  "summary": "Sequential decision-making in real-world applications often involves uncertainty about the environment's model. Uncertain Markov decision processes (UMDPs) represent the possible environments as a set of MDPs with shared states and actions but potentially different transition probabilities and rewards. Optimizing a single policy across all possible MDPs may sacrifice performance, while preparing an individually optimized policy for every MDP may violate operational, regulatory, or interpretabili",
  "authors": "Sterre Lutz, Daniël Vos, Matthijs T. J. Spaan, Anna Lukina",
  "category": "research",
  "topics": "regulation,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-03T17:08:02.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "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/16089",
  "original_url": "https://arxiv.org/abs/2608.02509v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}