We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

Reward and representation learning are two long-standing challenges for learning an
expanding set of robot manipulation skills from sensory observations. Given the inherent …

Large, high-capacity models trained on diverse datasets have shown remarkable successes
on efficiently tackling downstream applications. In domains from NLP to Computer Vision …

Recent unsupervised pre-training methods have shown to be effective on language and
vision domains by learning useful representations for multiple downstream tasks. In this …

Imitation learning from human demonstrations is a promising paradigm for teaching robots
manipulation skills in the real world. However, learning complex long-horizon tasks often …

While significant progress has been made on understanding hand-object interactions in
computer vision, it is still very challenging for robots to perform complex dexterous …

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

Passive observational data, such as human videos, is abundant and rich in information, yet
remains largely untapped by current RL methods. Perhaps surprisingly, we show that …