We study offline reinforcement learning (RL), which aims to learn an optimal policy based on
a dataset collected a priori. Due to the lack of further interactions with the environment …

Actor-critic methods are widely used in offline reinforcement learningpractice, but are not so
well-understood theoretically. We propose a newoffline actor-critic algorithm that naturally …

Reinforcement learning is a general technique that allows an agent to learn an optimal
policy and interact with an environment in sequential decision-making problems. The …

Understanding when reinforcement learning algorithms can make successful off-policy
predictions—and when the may fail to do so–remains an open problem. Typically, model …

This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn)
policies in scenarios where the data are collected from a distribution that substantially differs …

We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision
Processes (MDP). For tabular MDP with $ S $ states and $ A $ actions, or linear MDP with …

Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-
commerce, healthcare, and policymaking because they can both improve outcomes for …

Off-policy evaluation learns a target policy's value with a historical dataset generated by a
different behavior policy. In addition to a point estimate, many applications would benefit …

Off-policy evaluation (OPE) in reinforcement learning is an important problem in settings
where experimentation is limited, such as healthcare. But, in these very same settings …