Deepmind Technologies Limited

Lasse Espeholt

Karen Simonyan

Oriol Vinyals

Koray Kavukcuoglu

Aaron Gerard Antonius Van Den Oord

Sander Etienne Lea Dieleman

Timothy James Alexander Harley

Remi Munos

Hubert Josef Soyer

Volodymyr Mnih

Iain Robert Dunning

Yotam Doron

Vlad Firoiu

Thomas Ward

Nal Emmerich Kalchbrenner

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.

Distributed training using actor-critic reinforcement learning with off-policy correction factors

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sequences using convolutional neural networks. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.

Processing sequences using convolutional neural networks

Growing community of inventors

Amsterdam, Netherlands

Lasse Espeholt