English

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

Machine Learning 2020-10-27 v1 Econometrics Machine Learning

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.

Keywords

Cite

@article{arxiv.2010.13554,
  title  = {Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy},
  author = {Masahiro Kato and Yusuke Kaneko},
  journal= {arXiv preprint arXiv:2010.13554},
  year   = {2020}
}

Comments

arXiv admin note: text overlap with arXiv:2010.03792

R2 v1 2026-06-23T19:39:09.967Z