SOURCE-LINKED INTELLIGENCE

Robot World Models Are Not Invariant to How the Actions Are Written

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

A robot policy is trained with one of two action parameterizations: absolute joint targets, or deltas relative to the current state. The choice is a live engineering decision in robot learning, and a world model conditioned on actions inherits it silently. We show the inheritance is catastrophic. A latent dynamics model trained on one parameterization and handed the identical commanded trajectory written in the other collapses: retrieval degrades by 2.6-13.4x across three robot datasets and two morphologies, goal-conditioned action selection falls from 53% to 15%, and on PushT the two beliefs

Read original source ↗ Open in workspace

recordType

paper

region

Global