{
  "id": 4340,
  "url": "https://arxiv.org/abs/2605.14497v1",
  "title": "ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization",
  "summary": "Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distribution shift between offline datasets and the evolving online policy. Common approaches often rely on static mixing ratios or heuristic-based replay strategies, which lack adaptability to different environments and varying training dynamics, resulting in suboptimal tradeoff between stability and asymptotic performance.",
  "authors": "Letian Yang, Xu Liu, Yiqiang Lu, Jian Liu, Weiqiang Wang, Shuai Li",
  "category": "research",
  "topics": "regulation,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-14T07:35:58.000Z",
  "fetched_at": "2026-07-14T16:30:54.922Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4340",
  "original_url": "https://arxiv.org/abs/2605.14497v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}