About this paper
AFFECT, an auxiliary objective that trains world models to match visual responses to temporally correlated action noise, improves rollout fidelity and planning success in simulated and real robotic tasks.
World models aim to predict environment dynamics under actions, enabling the prediction of action consequences without executing them in the real world. Yet despite producing increasingly realistic videos, current world models often fail to capture how small action changes affect future observations. This limits their use in tasks such as robotic policy evaluation and model-based planning, where nearly identical actions can lead to qualitatively different outcomes. To address this, we propose AFFECT, an auxiliary training objective for learning the distribution of visual changes induced by action perturbations. Specifically, we inject temporally correlated noise into the actions of a…
world modelsenvironment dynamicsaction perturbationsauxiliary training objectivetemporally correlated noisepolicytask-agnostic human teleoperationworld-model rolloutsFVDmodel-based planning
- Upvotes
- 9
- Authors
- 3
- Published
- Nov 19, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Learning What Actions Change: Action Effect Matching for Dynamics-Faithful World Models was first seen on Hugging Face · Daily papers on Nov 20, 2026. Since then it has appeared in 29 checks on 3 different days. Its best position was #15 of 30, reached on Nov 20, 07:29 UTC. It is #19 right now, slipping from #18 to #19 over the last 6 checks.