{
  "id": 9068355,
  "title": "Lifted Bellman Linear Programming for Offline Reinforcement Learning",
  "url": "https://urgent.news/2026/09/21/lifted-bellman-linear-programming-for-offline-reinforcement-learning",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-21T12:27:23.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.24489v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Offline reinforcement learning (RL) typically trains a critic by minimizing a regression loss against bootstrapped value targets stabilized by target networks with exponential moving average (EMA) updates. Multi-step targets incorporate behavior-policy actions and therefore require off-policy correction. We instead impose in-sample Bellman optimality on the critic through inequality constraints.…",
  "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."
}