Recent work on neural algorithmic reasoning has investigated the reasoni...
Learning from large amounts of unsupervised data and a small amount of
s...
Despite recent progress made by self-supervised methods in representatio...
Many reinforcement learning (RL) agents require a large amount of experi...
We present an architecture that is effective for continual learning in a...
Self-supervised learning has emerged as a strategy to reduce the relianc...
Causal models can compactly and efficiently encode the data-generating
p...
In reinforcement learning, we can learn a model of future observations a...
Discovering and exploiting the causal structure in the environment is a
...
Discovering the causal structure among a set of variables is a fundament...
We propose a novel hierarchical generative model with a simple Markovian...
Performing exact posterior inference in complex generative models is oft...