The rapid rise in demand for training large neural network architectures...
We present an algorithm for local, regularized, policy improvement in
re...
Some of the most successful applications of deep reinforcement learning ...
We describe TF-Replicator, a framework for distributed machine learning
...
We present an off-policy actor-critic algorithm for Reinforcement Learni...
The recently-developed WaveNet architecture is the current state of the ...
PixelCNN achieves state-of-the-art results in density estimation for nat...