In reinforcement learning (RL), state representations are key to dealing...
Auxiliary tasks improve the representations learned by deep reinforcemen...
Many machine learning problems encode their data as a matrix with a poss...
We study the learning dynamics of self-predictive learning for reinforce...
In reinforcement learning, state representations are used to tractably d...
In most practical applications of reinforcement learning, it is untenabl...
Group equivariant neural networks are used as building blocks of group
i...
Thanks to the tractability of their likelihood, some deep generative mod...
The Variational Auto-Encoder (VAE) model has become widely popular as a ...