mlsanityData to 14 Oct 2026

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

arXiv 2609.33669 ↗First posted 27 Sep 2026cs.AI cs.GT cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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-zetarisk-zetautil. 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 α=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±0.0177 and violation rate 0.0178±0.0057.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

30 of 42 references.

References · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Trust Region Policy Optimizationcited by 2,580
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  4. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  5. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  6. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  7. 2017Constrained Policy Optimizationcited by 983
  8. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  9. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  10. 2019Conformal Prediction Under Covariate Shiftcited by 519
  11. 2015Policy Distillationcited by 440
  12. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
18 more
  1. 2022Conformal Risk Controlcited by 299
  2. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 288
  3. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  4. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
  5. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 233
  6. 2022Defining and Characterizing Reward Hackingcited by 203
  7. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 186
  8. 2018Residual Policy Learningcited by 164
  9. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 158
  10. 2017Safe Policy Improvement with Baseline Bootstrappingcited by 144
  11. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 114
  12. 2018Deep Counterfactual Regret Minimizationcited by 103
  13. 2021Distribution-free uncertainty quantification for classification under label shiftcited by 101
  14. 2019Distilling Policy Distillationcited by 84
  15. 2017Safe and Nested Subgame Solving for Imperfect-Information Gamescited by 41
  16. 2025PokerBench: Training Large Language Models to become Professional Poker Playerscited by 18
  17. 2016AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Gamescited by 8
  18. 2025Parametric Scaling Law of Tuning Bias in Conformal Predictioncited by 7

Built on by

Not cited yet.