{
  "id": 18778,
  "url": "https://arxiv.org/abs/2608.12063v1",
  "title": "Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL",
  "summary": "Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping. To bypass this limitation, we leverage Sample-based Model Predictive Control (SMPC) entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets. Because this data solves the fundamental exploration problem, we can train an off-policy RL agent",
  "authors": "Martin Schuck, Maks Sorokin, Simone Manni, Duy Ta, Angela P. Schoellig, Marco Hutter et al.",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T13:48:56.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18778",
  "original_url": "https://arxiv.org/abs/2608.12063v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}