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 …

Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong
assumptions on both the function classes (eg, Bellman-completeness) and the data …

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 …

Settling the sample complexity of model-based offline reinforcement learning Page 1 The
Annals of Statistics 2024, Vol. 52, No. 1, 233–260 https://doi.org/10.1214/23-AOS2342 © …

Two central paradigms have emerged in the reinforcement learning (RL) community: online
RL and offline RL. In the online RL setting, the agent has no prior knowledge of the …

We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has
access to an offline dataset and the ability to collect experience via real-world online …

Coverage conditions--which assert that the data logging distribution adequately covers the
state space--play a fundamental role in determining the sample complexity of offline …

We provide theoretical investigations into off-policy evaluation in reinforcement learning
using function approximators for (marginalized) importance weights and value functions. Our …

We make progress in a long-standing problem of batch reinforcement learning (RL):
learning Q* from an exploratory and polynomial-sized dataset, using a realizable and …

We study worst-case guarantees on the expected return of fixed-dataset policy optimization
algorithms. Our core contribution is a unified conceptual and mathematical framework for the …