Intelligent agents rely heavily on prior experience when learning a new task, yet most
modern reinforcement learning (RL) approaches learn every task from scratch. One …

Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still
impose a major challenge in offline robot control. While a number of prior methods aimed to …

Demonstration-guided reinforcement learning (RL) is a promising approach for learning
complex behaviors by leveraging both reward feedback and a set of target task …

Abstract We introduce Compositional Imitation Learning and Execution (CompILE): a
framework for learning reusable, variable-length segments of hierarchically-structured …

Video understanding calls for a model to learn the characteristic interplay between static
scene content and its dynamics: Given an image, the model must be able to predict a future …

Abstract This paper proposes Retrieval-Enhanced Asymmetric Diffusion (READ) for image-
based robot motion planning. Given an image of the scene READ retrieves an initial motion …

The ability to predict and plan into the future is fundamental for agents acting in the world. To
reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse …

We introduce a variational approach to learning and inference of temporally hierarchical
structure and representation for sequential data. We propose the Variational Temporal …

When autonomous vehicles are deployed on public roads, they will encounter countless and
diverse driving situations. Many manually designed driving policies are difficult to scale to …

The ability to plan into the future while utilizing only raw high-dimensional observations,
such as images, can provide autonomous agents with broad and general capabilities …