Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy

Abstract: 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 the policy based on past observations, the samples are not independent and identically distributed (i.i.d.). This paper tackles this problem by constructing an estimator from a martingale difference sequence (MDS) for the dependent samples. In the data-generating process, we do not assume the convergence of the policy, but the policy uses the same conditional probability of choosing an action during a certain period. Then, we derive an asymptotically normal estimator of the value of an evaluation policy. As another advantage of our method, the batch-based approach simultaneously solves the deficient support problem. Using benchmark and real-world datasets, we experimentally confirm the effectiveness of the proposed method.