SOURCE-LINKED INTELLIGENCE

Adaptive Rollout Truncation Based on Epistemic Uncertainty for Efficient Offline World Model Training

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Accurate neural world models are central to model-based robotics, where they enable robots to predict future states from previously observed trajectories. Multi-step autoregressive training improves long-horizon prediction, but fixed rollout horizons also increase computational cost and can amplify early training errors when the model is still inaccurate. Existing training schemes typically use the same rollout length throughout optimization, independent of the model's current predictive reliability. We propose an epistemic uncertainty-driven adaptive rollout strategy for offline world model t

Read original source ↗ Open in workspace

recordType

paper

region

Global