Deepmind Technologies Limited

Bilal Piot

Olivier Claude Pietquin

Charles Blundell

Nicolas Manfred Otto Heess

Mel Vecerik

Remi Munos

Jonathan Karl Scholz

Martin Riedmiller

Volodymyr Mnih

Thomas Lampe

Jacob Lee Menick

Thomas Rothoerl

Meire Fortunato

Mohammad Gheshlaghi Azar

Todd Andrew Hester

Wang Fumin

Joao Carreira

Simon Osindero

Adrià Puigdomènech Badia

Viorica Patraucean

Pablo Sprechmann

Zhaohan Guo

Alex Vitvitskyi

Steven James Kapturowski

Olivier Tieleman

Bernardo Avila Pires

Olivier Pietquin

Matej Vecerik

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 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

An off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Training action selection neural networks using apprenticeship

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network that is used to select actions to be performed by an agent interacting with an environment. In one aspect, the method comprises: receiving an observation characterizing a current state of the environment; processing the observation and an exploration importance factor using the action selection neural network to generate an action selection output; selecting an action to be performed by the agent using the action selection output; determining an exploration reward; determining an overall reward based on: (i) the exploration importance factor, and (ii) the exploration reward; and training the action selection neural network using a reinforcement learning technique based on the overall reward.

Jointly learning exploratory and non-exploratory action selection policies

Growing community of inventors

London, United Kingdom

Bilal Piot