Closing the Train-Test Gap in World Models for Gradient-Based Planning

Understand

World models paired with model predictive control (MPC) can be trained offline on large-scale datasets of expert trajectories and enable generalization to a wide range of planning tasks at inference time.

• Compared to traditional MPC procedures, which rely on slow search algorithms or on iteratively solving optimization problems exactly, gradient-based planning offers a computationally efficient alternative.
• However, the performance of gradient-based planning has thus far lagged behind that of other approaches.
• In this paper, we propose improved methods for training world models that enable efficient gradient-based planning.