← Back to homepage
World Models to Generate Diverse Training Data
Keshav Bardinath*, Stephen Zhu*, Shivansh Patel*, Svetlana Lazebnik, Unnat Jain
* denotes equal contribution

Abstract

World Models (WMs) have significant potential for robotics, particularly as a training engine for policy learning. In our approach, policies are executed autonomously inside the learned world model, allowing large amounts of interaction data to be generated without physical robot rollouts.

Below are bridge-trained policy rollouts generated by the world model:

Groot

Octo

CogAct

We use TopReward to filter good rollouts. We found it works well after some modifications. We aim to distill desirable behaviors from multiple policies into a single policy.