Bayesian Off-Policy Evaluation and Learning for Large Action Spaces

Imad Aouali, Victor-Emmanuel Brunel, David Rohde, Anna Korba

TL;DR: We use structured priors for efficient off-policy evaluation and learning. Algorithmic foundations are developed and an instance of the proposed algorithm is analyzed.

Abstract: In interactive systems, actions are often correlated, presenting an opportunity for more sample-efficient off-policy evaluation (OPE) and learning (OPL) in large action spaces. We introduce a unified Bayesian framework to capture these correlations through structured and informative priors. In this framework, we propose sDM, a generic Bayesian approach for OPE and OPL, grounded in both algorithmic and theoretical foundations. Notably, sDM leverages action correlations without compromising computational efficiency. Moreover, inspired by online Bayesian bandits, we introduce Bayesian metrics that assess the average performance of algorithms across multiple problem instances, deviating from the conventional worst-case assessments. We analyze sDM in OPE and OPL, highlighting the benefits of leveraging action correlations. Empirical evidence showcases the strong performance of sDM.

Submission Number: 42