Metraipolis › archive › dc_45149fab43bf

A Finite-Sample Analysis of Quantile Temporal-Difference Learning — arXiv:2608.27313

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27313
License (as archived)
CC0-1.0
Archived
2026-10-17T16:15:56.829Z
SHA-256 of the archived text
bb617104b0f659dc0b191eeb87190dcb82247777c1846b433c0cf48046b94927
Stable URL of this page
https://metraipolis.com/documento/dc_45149fab43bf

How to cite

A Finite-Sample Analysis of Quantile Temporal-Difference Learning — arXiv:2608.27313 — arXiv (en), https://arxiv.org/abs/2608.27313 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45149fab43bf (Metraipolis archive dc_45149fab43bf, sha256 bb617104b0f659dc0b191eeb87190dcb82247777c1846b433c0cf48046b94927)
BibTeX
@misc{dc45149fab43bf,
  title = {A Finite-Sample Analysis of Quantile Temporal-Difference Learning — arXiv:2608.27313},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27313},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45149fab43bf; sha256 bb617104b0f659dc0b191eeb87190dcb82247777c1846b433c0cf48046b94927},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27313. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 converges to the target at rate $T^{-a/2}$ in the infinity norm, up to logarithmic and lower-order terms. A suitably tuned harmonic schedule recovers the $T^{-1/2}$ statistical rate up to logarithmic factors. For the $m$-quantile representation, its $\infty$-Wasserstein error scales as $\sqrt{m/T}$ up to logarithmic factors, matching the leading polynomial dependence on the quantile resolution and sample size of the corresponding model-based estimator. The proof uses a two-stage global-to-local argument. From arbitrary initialization, Bellman contraction and CDF monotonicity first bring the iterate close to the target, after which, a novel variance--drift matching argument sharpens the control of accumulated noise and local contraction reduces the remaining errors, yielding the sharp rate. Simulations verify the predicted polynomial decay and assess the finite-time entrance bound.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.27313 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:34:50.020Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).