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 …

Reinforcement learning (RL) provides a theoretical framework for continuously improving an
agent's behavior via trial and error. However, efficiently learning policies from scratch can be …

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 model-based offline Reinforcement Learning with general function approximation
without a full coverage assumption on the offline data distribution. We present an algorithm …

In order to deal with the curse of dimensionality in reinforcement learning (RL), it is common
practice to make parametric assumptions where values or policies are functions of some low …

We show that computing approximate stationary Markov coarse correlated equilibria (CCE)
in general-sum stochastic games is PPAD-hard, even when there are two players, the game …

The success of reinforcement learning in a variety of challenging sequential decision-
making problems has been much discussed, but often ignored in this discussion is the …

We present BRIEE, an algorithm for efficient reinforcement learning in Markov Decision
Processes with block-structured dynamics (ie, Block MDPs), where rich observations are …

This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert
demonstrator without additional online environment interactions. Instead, the learner is …

Efficient exploration under sparse rewards remains a key challenge in deep reinforcement
learning. Previous exploration methods (eg, RND) have achieved strong results in multiple …