Generalization, defined as applying limited experiences to novel situations, represents a
cornerstone of human intelligence. Our review traces the evolution and continuity of …

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 …

A fundamental challenge in interactive learning and decision making, ranging from bandit
problems to reinforcement learning, is to provide sample-efficient, adaptive learning …

Abstract This work introduces Bilinear Classes, a new structural framework, which permit
generalization in reinforcement learning in a wide variety of settings through the use of …

We study reinforcement learning (RL) with linear function approximation where the
underlying transition probability kernel of the Markov decision process (MDP) is a linear …

Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in
two settings: learning interactively in the environment (online RL), or learning from an offline …

We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where
instead of receiving a numeric reward at each step, the RL agent only receives preferences …

Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian noise fail to
explore efficiently in some reinforcement learning tasks and yet, they perform well in many …

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 investigate the problem of corruption robustness in offline reinforcement learning (RL)
with general function approximation, where an adversary can corrupt each sample in the …