We present a framework that abstracts Reinforcement Learning (RL) as a
s...
We present VideoGPT: a conceptually simple architecture for scaling
like...
Self-attention has the promise of improving computer vision systems due ...
Novel computer vision architectures monopolize the spotlight, but the im...
Recent advances in off-policy deep reinforcement learning (RL) have led ...
We present BoTNet, a conceptually simple yet powerful backbone architect...
Building instance segmentation models that are data-efficient and can ha...
While improvements in deep learning architectures have played a crucial ...
A common practice in unsupervised representation learning is to use labe...
Model-free deep reinforcement learning (RL) has been successful in a ran...
Learning from visual observations is a fundamental yet challenging probl...
We present CURL: Contrastive Unsupervised Representations for Reinforcem...
Flow-based generative models are powerful exact likelihood models with
e...
A key challenge in complex visuomotor control is learning abstract
repre...