Article

PRISM: Prior-Guided Imagination Sampling in World Model Representations

The authors propose PRISM, which trains a lightweight action head on features from a frozen latent world model encoder to obtain a goal-conditioned action prior, then uses its mean and predicted uncertainty to guide action search, with the world model evaluating the consequences of actions. Experiments on four simulated control tasks and two real-robot platforms show that the lightweight action head improves planning performance, and that the same fusion interface can accept a diffusion prior over the same frozen features without modification.

Part of the event: PRISM: Extracting Action Priors from Frozen World Model Representations to Guide Planning

This page provides a summary and source link only.