SOURCE-LINKED INTELLIGENCE

A Finite-Sample Analysis of Quantile Temporal-Difference Learning

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Quantile temporal-difference learning (QTD) is an effective method for learning return distributions through quantile approximation, yet its finite-time behavior remains poorly understood. Its update is nonlinear and nonsmooth, and the stability needed for a sharp convergence rate holds only near the target. We establish a global high-probability last-iterate guarantee for synchronous tabular QTD under general positive, nonincreasing step-size sequences and arbitrary initialization in the natural parameter range. For polynomially decaying step sizes with exponent $a\in(0,1)$, the last iterate

Read original source ↗ Open in workspace

recordType

paper

region

Global