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 study the design of sample-efficient algorithms for reinforcement learning in the
presence of rich, high-dimensional observations, formalized via the Block MDP problem …

Self-supervised pretraining has been extensively studied in language and vision domains,
where a unified model can be easily adapted to various downstream tasks by pretraining …

In recent years, domains such as natural language processing and image recognition have
popularized the paradigm of using large datasets to pretrain representations that can be …

Informational parsimony provides a useful inductive bias for learning representations that
achieve better generalization by being robust to noise and spurious correlations. We …

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient,
adaptive, and explainable by learning an explicit model of the environment. While the …

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that
are capable of solving multiple tasks and reach a diverse set of objectives. How to\textit …

Learning to control an agent from data collected offline in a rich pixel-based visual
observation space is vital for real-world applications of reinforcement learning (RL). A major …

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that
are capable of solving multiple tasks and reach a diverse set of objectives. How to\textit …

Sample-efficiency and reliability remain major bottlenecks toward wide adoption of
reinforcement learning algorithms in continuous settings with high-dimensional perceptual …