{"slug": "lucid-latent-skill-unified-control-via-imagined-dynamics-for-long-horizon-loco", "title": "LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation", "summary": "Researchers introduced LUCID, a hierarchical model-based reinforcement learning framework for long-horizon humanoid loco-manipulation, which plans over reusable skills via imagined rollouts of a learned dynamics model. In simulated multi-object rearrangement tasks, LUCID improved full-task success and partial-completion rates over prior baselines, demonstrating its effectiveness in complex sequential tasks.", "body_md": "arXiv:2608.07746v1 Announce Type: new\nAbstract: Long-horizon humanoid loco-manipulation requires composing versatile whole-body skills and reliable high-level decision making. Existing methods often coordinate pretrained skills with scripted planners, finite-state machines or task-specific model-free policies, restricting their ability to handle complex task sequences. To address this limitation, we propose \\textbf{LUCID}, a hierarchical model-based reinforcement learning framework that plans over reusable skills through imagined rollouts of a learned dynamics model. LUCID first trains a structured latent-conditioned low-level policy via adversarial imitation and then freezes it while jointly learning a high-level policy and macro-dynamics world model. The world model predicts the temporally extended state transitions induced by latent decisions, enabling high-level policy optimization through imagined rollouts. We evaluate our framework across various simulated multi-object rearrangement scenarios. Experimental results show that LUCID improves the full-task success and partial-completion rates compared to prior baseline methods, demonstrating its effectiveness in complex sequential loco-manipulation tasks.", "url": "https://wpnews.pro/news/lucid-latent-skill-unified-control-via-imagined-dynamics-for-long-horizon-loco", "canonical_source": "https://arxiv.org/abs/2608.07746", "published_at": "2026-08-11 04:00:00+00:00", "updated_at": "2026-08-11 04:11:42.853023+00:00", "lang": "en", "topics": ["machine-learning", "robotics", "artificial-intelligence"], "entities": ["LUCID"], "alternates": {"html": "https://wpnews.pro/news/lucid-latent-skill-unified-control-via-imagined-dynamics-for-long-horizon-loco", "markdown": "https://wpnews.pro/news/lucid-latent-skill-unified-control-via-imagined-dynamics-for-long-horizon-loco.md", "text": "https://wpnews.pro/news/lucid-latent-skill-unified-control-via-imagined-dynamics-for-long-horizon-loco.txt", "jsonld": "https://wpnews.pro/news/lucid-latent-skill-unified-control-via-imagined-dynamics-for-long-horizon-loco.jsonld"}}