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 …

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 …

Develo** an agent capable of adapting to unseen environments remains a difficult
challenge in imitation learning. This work presents Adaptive Return-conditioned Policy …

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

Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's
knowledge about the underlying dynamics of the environment, enabling learning a world …

Recently, various pre-training methods have been introduced in vision-based
Reinforcement Learning (RL). However, their generalization ability remains unclear due to …

In pixel-based deep reinforcement learning (DRL), learning representations of states that
change because of an agent's action or interaction with the environment poses a critical …

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

We introduce a new family of video prediction models designed to support downstream
control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a …

Goal-conditioned planning benefits from learned low-dimensional representations of rich
observations. While compact latent representations typically learned from variational …