Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …

Few-Shot Learning refers to the problem of learning the underlying pattern in the data just
from a few training samples. Requiring a large number of data samples, many deep learning …

Fine manipulation tasks, such as threading cable ties or slotting a battery, are notoriously
difficult for robots because they require precision, careful coordination of contact forces, and …

Graph Attention Networks (GATs) are one of the most popular GNN architectures and are
considered as the state-of-the-art architecture for representation learning with graphs. In …

In this paper, we study the problem of enabling a vision-based robotic manipulation system
to generalize to novel tasks, a long-standing challenge in robot learning. We approach the …

Prompt-based learning has emerged as a successful paradigm in natural language
processing, where a single general-purpose language model can be instructed to perform …

Imitation learning from human demonstrations has shown impressive performance in
robotics. However, most results focus on table-top manipulation, lacking the mobility and …

Human can leverage prior experience and learn novel tasks from a handful of
demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve …

While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …