cs.RONov 2, 2026

Right Ranking, Wrong Scale: Reproducing the Robotic World Model's Dynamics Model and Testing the Uncertainty of Its Follow-up

Authors: Joyjeet Singh

Organizations: Independent Researcher, Chandigarh, India

Abstract

We reimplement the dynamics model of the Robotic World Model (RWM) and test the uncertainty estimate that its follow-up, RWM-U, uses to penalize reward in offline policy optimization. Our implementation matches the released model's gradients. On held-out data, training on the model's own rollouts beats one-step training at the preregistered long horizon for all ten episodes, but loses on short one-step windows. RWM-U's ensemble disagreement ranks rollout errors better than forecast step (Spearman rho = 0.90 at 100 steps), yet its spread substantially understates error: one-sigma coverage on the released checkpoint is 4.6% at 100 steps, versus 68% for a calibrated Gaussian. Rolling ensemble members on their own predictions raises coverage to 33%. The implemented squared-error loss on sampled predictions drives each member's variance toward zero. A horizon-specific rescaling restores one-sigma coverage under leave-one-episode-out evaluation, but not two-sigma coverage. We also identify two defects in the released evaluation pipeline. The study covers one robot, one gait and one dataset; it trains no policy.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation

    Jul 2, 2026GigaWorld Team, Angyuan Ma, Boyuan Wang +24Robot Foundation ModelsAction-Conditioned World Models

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

    Sep 18, 2026Nikodem Sebastian Zymla, Laurin Thiele, Johannes PitzWorld Model LearningWorld Models for Robotics