Metraipolis › archive › dc_fd746341c568

Feedback-Aware Tuning of Recursive Q-Learning — arXiv:2609.12716

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12716
License (as archived)
CC0-1.0
Archived
2026-10-16T03:43:44.884Z
SHA-256 of the archived text
fdea6f27566255275649814a5445cbadfbd977e7bcae417e1460a07b1d0c65b7
Stable URL of this page
https://metraipolis.com/documento/dc_fd746341c568

How to cite

Feedback-Aware Tuning of Recursive Q-Learning — arXiv:2609.12716 — arXiv (en), https://arxiv.org/abs/2609.12716 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd746341c568 (Metraipolis archive dc_fd746341c568, sha256 fdea6f27566255275649814a5445cbadfbd977e7bcae417e1460a07b1d0c65b7)
BibTeX
@misc{dcfd746341c568,
  title = {Feedback-Aware Tuning of Recursive Q-Learning — arXiv:2609.12716},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12716},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd746341c568; sha256 fdea6f27566255275649814a5445cbadfbd977e7bcae417e1460a07b1d0c65b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12716. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Model choice in backward Q-learning is recursive because a later-stage choice changes the response supplied to an earlier regression and can alter its model-comparison statistic. Separate stagewise criteria do not directly assess the target-stage prediction risk of a completed Q-learning fit. We address this mismatch by treating the entire backward-fitting rule as the unit of comparison and propose feedback-aware soft tuning for sequential multiple assignment randomised trials. Each backward fit uses its own generated responses and is assessed at a common prediction target. The risk criterion retains downstream effects on upstream comparisons, while a separate correction accounts for estimating the final exponential weights from the same observations. For a fixed finite library of smooth recursive maps, we establish an exact risk identity under a Gaussian shift model and an oracle inequality with an explicit adaptation remainder. Under coordinate-representation and moment conditions, these guarantees transfer to prediction risk at any prespecified stage, with the number of stages fixed as sample size increases. A two-stage construction supplies an explicit observable implementation. Numerical studies examine risk estimation and finite-sample performance, and a simulated attention-deficit/hyperactivity-disorder trial illustrates the relation between comparison feedback and treatment recommendations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in stat.ME).
Categorie arXiv: Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2609.12716 — 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 2026-10-16T03:14:51.929Z dalla pagina https://arxiv.org/catchup/stat.ME/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).