No AI summary available for this article.
Why It Matters
Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.06484v1 · Indexed 1 day ago