Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following
data have exhibited impressive language reasoning capabilities across various scenarios …

This work studies the problem of object goal navigation which involves navigating to an
instance of the given object category in unseen environments. End-to-end learning-based …

Training generally-capable agents with reinforcement learning (RL) remains a significant
challenge. A promising avenue for improving the robustness of RL agents is through the use …

The intertwined processes of learning and evolution in complex environmental niches have
resulted in a remarkable diversity of morphological forms. Moreover, many aspects of animal …

This work presents a modular and hierarchical approach to learn policies for exploring 3D
environments, calledActive Neural SLAM'. Our approach leverages the strengths of both …

A fundamental problem in computer animation is that of realizing purposeful and realistic
human movement given a sufficiently-rich set of motion capture clips. We learn data-driven …

Learning modular structures which reflect the dynamics of the environment can lead to better
generalization and robustness to changes which only affect a few of the underlying causes …

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to
maximize the accumulated reward, it often learns to exploit loopholes and misspecifications …

State representation learning, or the ability to capture latent generative factors of an
environment is crucial for building intelligent agents that can perform a wide variety of tasks …

Generalization is a central challenge for the deployment of reinforcement learning (RL)
systems in the real world. In this paper, we show that the sequential structure of the RL …