SOURCE-LINKED INTELLIGENCE

Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Offline policy evaluation (OPE) is crucial in high-stakes reinforcement learning applications, where new policies must be assessed reliably before deployment. In such settings, point estimates alone are insufficient; principled uncertainty quantification, such as confidence intervals and variance estimates, is essential for safe and risk-aware decision-making. A comprehensive way to unify these tasks is to estimate the sampling distribution of the evaluation error. Existing approaches, however, often suffer from limited robustness, scalability, or finite-sample validity. In this paper, we prop

Read original source ↗ Open in workspace

recordType

paper

region

Global