Hugging Face Papers ↗ · 2026-11-19
Learning What Actions Change: Action Effect Matching for Dynamics-Faithful World Models
Media reports Hugging Face Papers Source language: Chinese
AFFECT is an auxiliary objective that trains world models to match visual responses to temporally correlated action noise, improving rollout fidelity and planning success in simulated and real robotic tasks.
Full text
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.