Data-driven Distributionally Robust Control Based on Sinkhorn Ambiguity Sets

As the complexity of modern control systems increases, it becomes challenging to derive an accurate model of the uncertainty that affects their dynamics. Wasserstein Distributionally Robust Optimization (DRO) provides a powerful framework for decision-making under distributional uncertainty only using noise samples. However, while the resulting policies inherit strong probabilistic guarantees when the number of samples is sufficiently high, their performance may significantly degrade when only a few data are available. Inspired by recent results from the machine learning community, we introduce an entropic regularization to penalize deviations from a given reference distribution and study data-driven DR control over Sinkhorn ambiguity sets. We show that for finite-horizon control problems, the optimal DR linear policy can be computed via convex programming. By analyzing the relation between the ambiguity set defined in terms of Wasserstein and Sinkhorn discrepancies, we reveal that, as the regularization parameter increases, this optimal policy interpolates between the solution of the Wasserstein DR problem and that of the stochastic problem under the reference distribution. We validate our theoretical findings and the effectiveness of our approach when only scarce data are available on a numerical example.