Deepmind Technologies Limited

Gdm Holding LLC

Volodymyr Mnih

Koray Kavukcuoglu

Timothy James Alexander Harley

Remi Munos

Bilal Piot

Karen Simonyan

David Silver

Alexander Benjamin Graves

Charles Blundell

Adrià Puigdomènech Badia

Simon Osindero

Joao Carreira

Hubert Josef Soyer

Jacob Lee Menick

Iain Robert Dunning

Olivier Claude Pietquin

Meire Fortunato

Viorica Patraucean

Yotam Doron

Vlad Firoiu

Thomas Ward

Mohammad Gheshlaghi Azar

Lasse Espeholt

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using recurrent attention. One of the methods includes determining a location in the first image; extracting a glimpse from the first image using the location; generating a glimpse representation of the extracted glimpse; processing the glimpse representation using a recurrent neural network to update a current internal state of the recurrent neural network to generate a new internal state; processing the new internal state to select a location in a next image in the image sequence after the first image; and processing the new internal state to select an action from a predetermined set of possible actions.

Generating predictions characterizing images using glimpses extracted from the images

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

A system that is configured to receive a sequence of task inputs and to perform a machine learning task is described. The system includes a reinforcement learning (RL) neural network and a task neural network. The RL neural network is configured to: generate, for each task input of the sequence of task inputs, a respective decision that determines whether to encode the task input or to skip the task input, and provide the respective decision of each task input to the task neural network. The task neural network is configured to: receive the sequence of task inputs, receive, from the RL neural network, for each task input of the sequence of task inputs, a respective decision that determines whether to encode the task input or to skip the task input, process each of the un-skipped task inputs in the sequence of task inputs to generate a respective accumulated feature for the un-skipped task input, wherein the respective accumulated feature characterizes features of the un-skipped task input and of previous un-skipped task inputs in the sequence, and generate a machine learning task output for the machine learning task based on the last accumulated feature generated for the last un-skipped task input in the sequence.

Reinforcement learning for active sequence processing

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network.

Reinforcement learning using baseline and policy neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent. The method includes obtaining an observation characterizing a current state of an environment. For each layer parameter of each noisy layer of a neural network, a respective noise value is determined. For each layer parameter of each noisy layer, a noisy current value for the layer parameter is determined from a current value of the layer parameter, a current value of a corresponding noise parameter, and the noise value. A network input including the observation is processed using the neural network in accordance with the noisy current values to generate a network output for the network input. An action is selected from a set of possible actions to be performed by the agent in response to the observation using the network output.

Noisy neural network layers with noise parameters

Image processing of an environment to select an action to be performed by an agent interacting with the environment

Growing community of inventors

Toronto, Canada

Volodymyr Mnih