We study sequential decision making in environments where rewards are only partially
observed, but can be modeled as a function of observed contexts and the chosen action by …

Off-policy evaluation (OPE) is the problem of estimating the value of a target policy from
samples obtained via different policies. Recently, applying OPE methods for bandit …

We propose a novel evaluation methodology for assessing off-policy learning methods in
contextual bandits. In particular, we provide a way to use data from any given Randomized …

We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where
the goal is to estimate the performance of a policy from the data generated by another policy …

This work investigates the offline formulation of the contextual bandit problem, where the
goal is to leverage past interactions collected under a behavior policy to evaluate, select …

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy
Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of …

Abstract Off-Policy Evaluation (OPE) in contextual bandits is crucial for assessing new
policies using existing data without costly experimentation. However, current OPE methods …

Algorithmic recommendations and decisions have become ubiquitous in today's society.
Many of these and other data-driven policies, especially in the realm of public policy, are …

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data
obtained via a behavior policy. However, because the contextual bandit algorithm updates …

Off-policy evaluation (OPE) in both contextual bandits and reinforcement learning allows
one to evaluate novel decision policies without needing to conduct exploration, which is …