{
  "id": 16134,
  "url": "https://arxiv.org/abs/2608.00175v1",
  "title": "Inference-Time Policy Alignment for Fair Reinforcement Learning",
  "summary": "Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions. However, once deployed, the policies of these RL agents are often rigid and costly to adapt to new performance criteria. For instance, an agent trained to maximize expected cumulative reward may not accommodate previously unknown stakeholder preferences. Existing approaches to achieve fairness, a type of preference, in RL typically assume that such preferences are known a priori and require",
  "authors": "Umer Siddique, Peilang Li, Conor Wallace, Yongcan Cao",
  "category": "research",
  "topics": "bias-fairness,regulation,safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-31T18:00:50.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "x-arxiv-fairness-query",
  "source_name": "arXiv fairness query",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/16134",
  "original_url": "https://arxiv.org/abs/2608.00175v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}