{
  "id": 7581,
  "url": "https://arxiv.org/abs/2603.06565v1",
  "title": "Boosting deep Reinforcement Learning using pretraining with Logical Options",
  "summary": "Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans' ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based ",
  "authors": "Zihan Ye, Phil Chau, Raban Emunds, Jannis Blüml, Cedric Derstroff, Quentin Delfosse et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-06T18:55:15.000Z",
  "fetched_at": "2026-07-14T16:33:21.047Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7581",
  "original_url": "https://arxiv.org/abs/2603.06565v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}