{
  "id": 20845821,
  "title": "Demonstration-Free Skill Composition for Navigation and Manipulation",
  "url": "https://urgent.news/2026/11/19/demonstration-free-skill-composition-for-navigation-and-manipulation",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-19T03:47:02.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.25462v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Hierarchical reinforcement learning enables sequential tasks to be represented as compositions of separately trained skills. This paper evaluates demonstration-free hierarchical pipelines for MiniGrid navigation and robotic manipulation, comparing their training requirements and task performance with flat reinforcement learning baselines. The evaluation concerns complete pipelines with…",
  "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."
}