RESEARCH PAPER

Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

Jai Bardhan; Patrik Drozdik; Josef Sivic; Vladimir Petrik

Classification

View four quadrants
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. PersistWorld post-trains Ctrl-World to improve action-conditioned multi-view video rollouts using ground-truth fidelity rewards. Actions come from recorded trajectories or separate policies; the model remains an observation simulator. Its simulator-specific post-training does not make it a canonical component. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX