Unsupervised pre-training has recently become the bedrock for computer vision and natural
language processing. In reinforcement learning (RL), goal-conditioned RL can potentially …

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 …

We propose BOSS, an approach that automatically learns to solve new long-horizon,
complex, and meaningful tasks by growing a learned skill library with minimal supervision …

While natural language offers a convenient shared interface for humans and robots,
enabling robots to interpret and follow language commands remains a longstanding …

In the field of unsupervised skill discovery (USD), a major challenge is limited exploration,
primarily due to substantial penalties when skills deviate from their initial trajectories. To …

Diffusion-based generative methods have proven effective in modeling trajectories with
offline datasets. However, they often face computational challenges and can falter in …

Combining gradient-based trajectory optimization with differentiable physics simulation is an
efficient technique for solving soft-body manipulation problems. Using a well-crafted …

Robot learning methods have recently made great strides, but generalization and
robustness challenges still hinder their widespread deployment. Failing to detect and …

Pre-training on task-agnostic large datasets is a promising approach for enhancing the
sample efficiency of reinforcement learning (RL) in solving complex tasks. We present …

In this work, we aim to learn dexterous manipulation of deformable objects using multi-
fingered hands. Reinforcement learning approaches for dexterous rigid object manipulation …