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

2026-09-27

AI Summary

This study addresses the heterogeneous degradation and vulnerability of residual policies under distribution shift caused by fixed groupings. We propose an adaptive structural certification framework that freezes the residual family prior to label injection, learns policy-visible partitions, and introduces a hybrid robustness selection mapping. By integrating weighted simultaneous certificates, robust mapping selection over pre-declared uncertainty sets, and deterministic auditing techniques, the framework jointly guarantees risk upper bounds and utility. Experimental results demonstrate that the proposed approach significantly improves weak-response utility, reduces the violation rate to 0.0059, and achieves high-probability satisfaction of risk budgets.

Abstract

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 $0.0178\pm0.0057$.

Problem

• residual policy adaptation
• imperfect-information games
• distribution shift
• risk-utility certification
• heterogeneous degradation

Innovation

• Residual Policy Adaptation
• Risk-Utility Certification
• Structure-Adaptive Partitioning
• Distribution Shift Robustness
• Imperfect-Information Games