Gradient-based Planning for World Models at Longer Horizons
BAIR
Researchers propose GRASP, a gradient-based planning method for world models that addresses long-horizon planning challenges by optimizing over both actions and states in parallel, adding stochasticity for exploration, and reshaping gradients to avoid brittle state-input optimization through vision models. The method lifts the dynamics constraint to a soft penalty, enabling parallel computation across time steps and avoiding exponential Jacobian conditioning from sequential rollouts that causes exploding/vanishing gradients. By treating states as optimization variables rather than computed through repeated model applications, GRASP mitigates adversarial robustness vulnerabilities in deep learning-based dynamics models that make naive state optimization unstable.
Why it matters
.grasp-results-table table { font-size: 0.875rem; line-height: 1.35; width: 100%; } .grasp-results-table th, .grasp-results-table td { padding: 0.35rem 0.5rem; } /* Consistent whitespace between major sections (this post is long and hr-heavy) */ article.post-content h2 { margin-top: 2.75rem; margin-bottom: 0.75rem; } article.post-content h2:first-of-type { margin-top: 2.25rem; } article.post-content h3 { margin-top: 1.65rem; margin-bottom: 0.5rem; } article.post-content hr { margin-top: 2.5rem; margin-bottom: 2.5rem; } GRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3) reshaping gradients so actions get clean signals while we avoid brittle “state-input” gradients through high-dimensional vision models. Large, learned world models are becoming increa
