We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning,
where the goal is to estimate a confidence interval on a target policy's value, given only …

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear
function approximation, which aims to estimate the value function of a target policy based on …

In many reinforcement learning applications, it is desirable to determine confidence interval
lower bounds on the performance of any given policy without executing said policy. In this …

Off-policy evaluation learns a target policy's value with a historical dataset generated by a
different behavior policy. In addition to a point estimate, many applications would benefit …

In this paper we present a new way of predicting the performance of a reinforcement
learning policy given historical data that may have been generated by a different policy. The …

We provide theoretical investigations into off-policy evaluation in reinforcement learning
using function approximators for (marginalized) importance weights and value functions. Our …

Motivated by the many real-world applications of reinforcement learning (RL) that require
safe-policy iterations, we consider the problem of off-policy evaluation (OPE)---the problem …

Bootstrapping provides a flexible and effective approach for assessing the quality of batch
reinforcement learning, yet its theoretical properties are poorly understood. In this paper, we …

This paper studies the statistical theory of off-policy evaluation with function approximation in
batch data reinforcement learning problem. We consider a regression-based fitted Q …

We consider the problem of off-policy evaluation for reinforcement learning, where the goal
is to estimate the expected reward of a target policy $\pi $ using offline data collected by …