Off-Policy Evaluation of Slate Policies under Bayes Risk

TL;DR

This paper introduces a new off-policy evaluation method for slate bandits that minimizes Bayes risk, demonstrating significant improvements over existing estimators, especially with diverse slot sizes.

Contribution

It proposes a novel estimator within the additive family that guarantees lower risk than the pseudoinverse estimator, with risk reduction growing linearly with the number of slots.

Findings

New estimator guarantees lower Bayes risk than PI estimator.

Risk improvement scales linearly with number of slots.

Maximal gains occur with diverse slot sizes in slate problems.

Abstract

We study the problem of off-policy evaluation for slate bandits, for the typical case in which the logging policy factorizes over the slots of the slate. We slightly depart from the existing literature by taking Bayes risk as the criterion by which to evaluate estimators, and we analyze the family of 'additive' estimators that includes the pseudoinverse (PI) estimator of Swaminathan et al.\ (2017; arXiv:1605.04812). Using a control variate approach, we identify a new estimator in this family that is guaranteed to have lower risk than PI in the above class of problems. In particular, we show that the risk improvement over PI grows linearly with the number of slots, and linearly with the gap between the arithmetic and the harmonic mean of a set of slot-level divergences between the logging and the target policy. In the typical case of a uniform logging policy and a deterministic target policy, each divergence corresponds to slot size, showing that maximal gains can be obtained for slate problems with diverse numbers of actions per slot.