<ul><li>Distributionally robust policy learning aims to find a policy that performs well under the worst-case distributional shift.</li><li>Existing methods for robust policy learning consider the worst-case joint distribution of the covariate and the outcome, which can be unnecessarily conservative.</li><li>This paper focuses on robust policy learning under concept drift, where only the conditional relationship between the outcome and the covariate changes.</li><li>The paper proposes a learning algorithm that maximizes the estimated policy value within a given policy class, with an optimal sub-optimality gap.</li></ul>

Distributionally Robust Policy Learning under Concept Drifts

Discover more