SOURCE-LINKED INTELLIGENCE

Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible. SmoothCruiser achieves problem-independent complexity $\widetilde O(\varepsilon^{-4})$ by exploiting the smoothness of the entropy-regularized Bellman backup, but its estimator is only first-order. We show that the sample-complexity exponent of SmoothCruiser-type planners is governed by the order $β$ of the local Taylor remainder, giving oracle complexity $\widetilde O(\varepsilon^{-(2+2/(β-1))})$: the first-order case $β=2$ recovers SmoothCruiser, while a second-order/cubic remaind

Read original source ↗ Open in workspace

recordType

paper

region

Global