Nonparametric Adaptive Robust Control Under Model Uncertainty

TL;DR

This paper introduces a nonparametric adaptive robust control method that combines online learning, empirical distribution, Wasserstein balls, and machine learning to handle model uncertainty in stochastic control problems, demonstrated through utility maximization.

Contribution

It develops a novel nonparametric adaptive robust control framework that integrates online learning and Wasserstein-based uncertainty sets with efficient computation techniques.

Findings

The proposed method outperforms traditional robust control approaches.

It effectively reduces uncertainty through online learning.

Numerical results validate the approach's superiority in utility maximization.

Abstract

We consider a discrete time stochastic Markovian control problem under model uncertainty. Such uncertainty not only comes from the fact that the true probability law of the underlying stochastic process is unknown, but the parametric family of probability distributions which the true law belongs to is also unknown. We propose a nonparametric adaptive robust control methodology to deal with such problem. Our approach hinges on the following building concepts: first, using the adaptive robust paradigm to incorporate online learning and uncertainty reduction into the robust control problem; second, learning the unknown probability law through the empirical distribution, and representing uncertainty reduction in terms of a sequence of Wasserstein balls around the empirical distribution; third, using Lagrangian duality to convert the optimization over Wasserstein balls to a scalar optimization problem, and adopting a machine learning technique to achieve efficient computation of the optimal control. We illustrate our methodology by considering a utility maximization problem. Numerical comparisons show that the nonparametric adaptive robust control approach is preferable to the traditional robust frameworks.