SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift

arXiv:2610.20473 · cs.AI, cs.GT, cs.LG · Submitted 2026-10-14 · Read on arXiv

cs.AI, cs.GT, cs.LG

Submitted: 2026-10-14

Updated: 2026-10-16

Comments: 16 pages, 8 figures

Project page: https://bowlingmh.github.io/publications/b2hd-05uai.html

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 9 episodes

Sources

• StratFormer: Adaptive Opponent Modeling and Exploitation in Imperfect-Information Games
• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
• OpenSpiel: A Framework for Reinforcement Learning in Games
• Proximal Policy Optimization Algorithms
• Solving Large Imperfect Information Games Using CFR+
• Using Common Random Numbers for Simulation-based Planning with Rollouts

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems