Deep neural networks are the most commonly used function approximators i...
Actor-critic algorithms that make use of distributional policy evaluatio...
Offline methods for reinforcement learning have the potential to help br...
Deep reinforcement learning has led to many recent-and
groundbreaking-ad...
Gating mechanisms are widely used in neural network models, where they a...
This paper introduces R2D3, an agent that makes efficient use of
demonst...
Texture synthesis techniques based on matching the Gram matrix of featur...
The TensorFlow Distributions library implements a vision of probability
...
We present a new, fully generative model of optical telescope image sets...
We develop stochastic variational inference, a scalable algorithm for
ap...
We present a hybrid algorithm for Bayesian topic models that combines th...
Variational methods are widely used for approximate posterior inference....