Finding the minimal structural assumptions that empower sample-efficient learning is one of
the most important research directions in Reinforcement Learning (RL). This paper …

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

Policy gradient (PG) methods are among the most effective methods in challenging
reinforcement learning problems with large state and/or action spaces. However, little is …

Value-function approximation methods that operate in batch mode have foundational
importance to reinforcement learning (RL). Finite sample guarantees for these methods …

This work studies the question of Representation Learning in RL: how can we learn a
compact low-dimensional representation such that on top of the representation we can …

We study reinforcement learning (RL) with linear function approximation. For episodic time-
inhomogeneous linear Markov decision processes (linear MDPs) whose transition …

We study the exploration problem with approximate linear action-value functions in episodic
reinforcement learning under the notion of low inherent Bellman error, a condition normally …

Modern deep learning methods provide effective means to learn good representations.
However, is a good representation itself sufficient for sample efficient reinforcement …

We study the exploration problem in episodic MDPs with rich observations generated from a
small number of latent states. Under certain identifiability assumptions, we demonstrate how …

We study the sample complexity of model-based reinforcement learning (henceforth RL) in
general contextual decision processes that require strategic exploration to find a near …