Reinforcement learning (RL) is one of the most vibrant research frontiers in machine
learning and has been recently applied to solve a number of challenging problems. In this …

MDPs with low-rank transitions—that is, the transition matrix can be factored into the product
of two matrices, left and right—is a highly representative structure that enables tractable …

In this paper, we study nonparametric estimation of instrumental variable (IV) regressions.
Recently, many flexible machine learning methods have been developed for instrumental …

We consider offline reinforcement learning (RL) where we only have only access to offline
data. In contrast to numerous offline RL algorithms that necessitate the uniform coverage of …

Off-policy evaluation (OPE) in reinforcement learning is notoriously difficult in long-and
infinite-horizon settings due to diminishing overlap between behavior and target policies. In …

Theoretical guarantees in reinforcement learning (RL) are known to suffer multiplicative
blow-up factors with respect to the misspecification error of function approximation. Yet, the …

Offline reinforcement learning is important in many settings with available observational data
but the inability to deploy new policies online due to safety, cost, and other concerns. Many …

We study the problem of offline decision making, which focuses on learning decisions from
datasets only partially correlated with the learning objective. While previous research has …

We study learning optimal policies from a logged dataset, ie, offline RL, with function
approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample …

Reinforcement Learning (RL) is an area of machine learning where an intelligent agent
solves sequential decision-making problems based on experience. Recent advances in the …