Metraipolis › archive › dc_ecc79efaf79c

RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games — arXiv:2609.33669

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33669
License (as archived): CC0-1.0
Archived: 2026-10-07T20:57:00.414Z
SHA-256 of the archived text: 40465e04c7cf98753df5a2330def7aee7a82ab04cbc7877dd93872c26006dcc3
Stable URL of this page: https://metraipolis.com/documento/dc_ecc79efaf79c

How to cite

RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games — arXiv:2609.33669 — arXiv (en), https://arxiv.org/abs/2609.33669 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecc79efaf79c (Metraipolis archive dc_ecc79efaf79c, sha256 40465e04c7cf98753df5a2330def7aee7a82ab04cbc7877dd93872c26006dcc3)

BibTeX

@misc{dcecc79efaf79c,
  title = {RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games — arXiv:2609.33669},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33669},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecc79efaf79c; sha256 40465e04c7cf98753df5a2330def7aee7a82ab04cbc7877dd93872c26006dcc3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33669. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Residual policy adaptation provides a lightweight way to modify a strong reference policy, but a shared scale and a fixed subgroup partition can hide heterogeneous degradation and become fragile when the deployment mixture of information states changes. We introduce RSD-Poker, a structure-adaptive and shift-robust certification framework that freezes a bank of residual families and scales, learns a policy-visible partition on an independent structure split, and freezes that partition before calibration labels are joined. Each candidate-group pair receives a weighted simultaneous upper certificate for anchor-relative risk and a lower certificate for weak-response utility. A robust group-to-candidate map is then selected over a predeclared uncertainty set of deployment group proportions. Under independent calibration units drawn from each frozen group's law, a candidate bank and partition fixed before calibration, and invariant within-group conditionals, the selected map satisfies its declared mixture-robust risk budget and utility certificate with probability at least $1-\zeta_{risk}-\zeta_{util}$. The information contract supports both a teacher-backed transform and a teacher-free observation-only student. The retained deterministic 24-state audit remains an exact replay diagnostic: empirical-zero selects $\alpha=0.08$, raising the weak-response proxy from 4.2082 to 4.2889 with $0/12$ held-out threshold crossings. On stratified held-out states, the learned-partition dual selector raises weak utility from 4.4074 under global dual certification to 4.4936 and lowers held-out violation from 0.0215 to 0.0078; its mixture-robust variant reaches violation 0.0059. Across five observation-only checkpoints, risk-calibrated residuals attain weak utility $4.3659\pm0.0177$ and violation rate $0.0178\pm0.0057$.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33669 — 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 2026-10-07T20:29:01.333Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).