{"ID":2830859,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.09929","arxiv_id":"2512.09929","title":"Closing the Train-Test Gap in World Models for Gradient-Based Planning","abstract":"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. We begin with the observation that although a world model is trained on a next-state prediction objective, it is used at test-time to instead estimate a sequence of actions. The goal of our work is to close this train-test gap. To that end, we propose train-time data synthesis techniques that enable significantly improved gradient-based planning with existing world models. At test time, our approach outperforms or matches the classical gradient-free cross-entropy method (CEM) across a variety of object manipulation and navigation tasks in 10% of the time budget.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.09929","url_pdf":"https://arxiv.org/pdf/2512.09929v1","authors":"[\"Arjun Parthasarathy\",\"Nimit Kalra\",\"Rohun Agrawal\",\"Yann LeCun\",\"Oumayma Bounou\",\"Pavel Izmailov\",\"Micah Goldblum\"]","published":"2025-12-10T18:59:45Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.RO\"]","methods":"[]","has_code":false}