Three major challenges in reinforcement learning are the complex dynamical systems with
large state spaces, the costly data acquisition processes, and the deviation of real-world …

The sim-to-real gap, which represents the disparity between training and testing
environments, poses a significant challenge in reinforcement learning (RL). A promising …

We consider the penalized distributionally robust optimization (DRO) problem with a closed,
convex uncertainty set, a setting that encompasses learning using f-DRO and spectral/L-risk …

We consider the penalized distributionally robust optimization (DRO) problem with a closed,
convex uncertainty set, a setting that encompasses the $ f $-DRO, Wasserstein-DRO, and …

We study the problem of learning a single neuron with respect to the $ L_2^ 2$-loss in the
presence of adversarial distribution shifts, where the labels can be arbitrary, and the goal is …

We introduce a new family of distances, relative-translation invariant Wasserstein distances
($ RW_p $), for measuring the similarity of two probability distributions under distribution …

We develop a generic policy gradient method with the global optimality guarantee for robust
Markov Decision Processes (MDPs). While policy gradient methods are widely used for …

This paper presents a novel Wasserstein distributionally robust control and state estimation
algorithm for partially observable linear stochastic systems, where the probability …

In this paper, we propose a distributionally robust safety verification method for Markov
decision processes where only an ambiguous transition kernel is available instead of the …

We introduce a framework that represents a dynamic program as a family of operators acting
on a partially ordered set. We provide an optimality theory based only on order-theoretic …