SOURCE-LINKED INTELLIGENCE

Optimal Value Inference for Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

We study offline inference for the optimal value in reinforcement learning under finite state and action spaces. Two new nuisances are derived as fixed points of a self-induced Bellman equation, in which we approximate the maximum Bellman operator by its softmax correspondence. We propose a debiased estimator through the Neyman orthogonality and establish its asymptotic normality under diverging horizons even when the behavior policy changes with time, as long as the nuisances have the statistical rates that can be achieved by many machine learning methods. We provide a concrete estimating pro

Read original source ↗ Open in workspace

recordType

paper

region

Global