arXiv cs.AI· Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Rui Chen, Daren Zha·· 12 小时前AI 评分18
SafeAdapt-Poker：对手行为漂移下预算化自适应的反事实风险校准
SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift
AI 导读
SafeAdapt-Poker 将对手行为漂移下的预算化自适应建模为双重反事实序贯控制问题，仅用每次决策前可得的信息，通过单调战略风险模型与配对预算状态延续模型权衡即时自适应收益与未来预算消耗。
正文 · 原文
Abstract:Opponent histories can mislead after behavioral shifts. SafeAdapt-Poker formulates budgeted adaptation under opponent shift as a dual-counterfactual sequential-control problem using only information available before each decision. At each decision the controller asks two distinct questions: what local downside a deviation from the frozen anchor would induce under matched legal continuations, and what future adaptation value would be lost by consuming part of the remaining deviation budget now. The first question is answered by a monotone strategic-risk model over deviation intensity; the second by a paired budget-state continuation model that prices current budget consumption. The controller selects among support-preserving candidate deviations by trading immediate adaptation value against these two quantities, a pathwise cumulative-KL ledger bounds total anchor-relative deviation, and a finite family of frozen controllers is screened on complete paired calibration sessions before held-out interaction. A finite-candidate perturbation bound shows that the allocation objective degrades continuously with continuation-value estimation error. Evaluation covers exact-game exploitation and safety, four opponent shifts, local-risk calibration, delayed-opportunity allocation, direct opportunity-value estimation, value-error robustness, factorial mechanism attribution, budget sensitivity, abstract-HUNL cross-play, and player/time-held-out public-history behavior. On exact Leduc the full controller attains a matched weak-pool gain of +0.0718 with a worst-opponent delta of -0.0126, raises delayed-opportunity capture from 0.6318 under myopic allocation to 0.7841 under the same session budget, and reaches +42.7 mbb/hand in abstract-HUNL cross-play; the retained public-history screen reports 0.5820 action accuracy and 0.9277 log loss versus 0.5039 and 0.9778 for a public prior.
| Comments: | 16 pages, 8 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20473 [cs.AI] |
| (or arXiv:2610.20473v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20473 arXiv-issued DOI via DataCite |
Submission history
From: Miaobo Hu [view email]
[v1]
Wed, 14 Oct 2026 16:50:42 UTC (376 KB)
[v2]
Fri, 16 Oct 2026 09:57:23 UTC (376 KB)
来源：arXiv cs.AI · arxiv.org