… of Efron’s bootstrap for computing confidence intervals with respect to the direct method (DM)
for off-policy evaluation. Our theoretical results show that Efron’s bootstrap is valid given …

… bootstrapping in off-policy evaluation (OPE), and in particular, we focus on the fitted Q-evaluation
(… the on-policy case, our bootstrap-based confidence interval still has a clear advantage …

… For critical applications, this might be troublesome [94] and thus necessitates obtaining
confidence intervals … Statistical Bootstrapping: An important advantage of having constructed an …

… -confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal
is to estimate a confidence interval on … inequalities and the bootstrap applied to importance …

… on-policy (TD) and off-policy (GTD) reinforcement learning algorithms. Second, we prove
that the confidence intervals constructed using our bootstrap algorithm are asymptotically valid. …

… non-asymptotic confidence intervals in infinite-horizon off-policy evaluation, which remains a
… , bootstrapping is time consuming since it requires to repeat the whole off-policy evaluation …

… interval. That said, these generalization bounds are typically loose for practical purposes, and
we handle statistical errors by bootstrapping … practically useful confidence intervals that are …

… We propose an off-policy evaluation method connecting off-policy evaluation to estimating
validation error for a positive-unlabeled (… Shaded regions are a 95% confidence interval. P γt0 …

… We consider a model-based approach to perform batch off-policy evaluation in reinforcement
learning. Our method takes a mixture-… Bootstrapping with models: Confidence intervals for …

… significantly from having a confidence interval (CI) that quantifies … This motivates us to study
the off-policy evaluation (OPE) … This is because the standard bootstrap method is not valid …