Metraipolis › archive › dc_0ba217b2d5ab
Online Inference in Distributional Temporal-Difference Learning — arXiv:2608.14408
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14408
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:30:52.148Z
- SHA-256 of the archived text
c42cedbee66d400a646c246aec5b1a2d4116635350e1e08b6c7ebbb2439542ac- Stable URL of this page
https://metraipolis.com/documento/dc_0ba217b2d5ab
How to cite
Online Inference in Distributional Temporal-Difference Learning — arXiv:2608.14408 — arXiv (en), https://arxiv.org/abs/2608.14408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ba217b2d5ab (Metraipolis archive dc_0ba217b2d5ab, sha256 c42cedbee66d400a646c246aec5b1a2d4116635350e1e08b6c7ebbb2439542ac)
BibTeX
@misc{dc0ba217b2d5ab,
title = {Online Inference in Distributional Temporal-Difference Learning — arXiv:2608.14408},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14408},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ba217b2d5ab; sha256 c42cedbee66d400a646c246aec5b1a2d4116635350e1e08b6c7ebbb2439542ac},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study online statistical inference for functionals of the return distribution under a fixed policy. The return distribution is estimated by nonparametric distributional temporal-difference learning from a single Markov trajectory. For the Polyak--Ruppert averaged estimator, we prove that its root-$T$ error converges weakly to a centered Gaussian random element in Cramér space. We also prove that, conditionally on the observed trajectory, the root-$T$ difference between the bootstrap and original averages converges weakly to the same Gaussian limit. These results justify bootstrap inference for smooth statistical functionals, including variance, CVaR, expected shortfall, and expectiles. For nonsmooth statistical functionals, we develop a local asymptotic theory for the estimated return CDF over $T^{-1/2}$-neighborhoods of finitely many thresholds, together with its bootstrap analogue. This theory allows us to conduct inference for nonsmooth statistical functionals characterized by CDF equations, including return quantiles.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14408 — 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 2026-10-19T02:26:17.841Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).