Deepmind Technologies Limited

Arthur Clement Guez

Oriol Vinyals

Nicolas Manfred Otto Heess

Razvan Pascanu

Danilo Jimenez Rezende

Yujia Li

Daniel Pieter Wierstra

Adrià Puigdomènech Badia

Theophane Guillaume Weber

Peter William Battaglia

Ilya Sutskever

David Silver

Hado Philip Van Hasselt

Sebastien Henri Andre Racaniere

David Paul Reichert

Lars Buesing

Karol Gregor

Thore Kurt Hartwig Graepel

Laurent Sifre

Christopher Maddison

Adria Puigdomenech Badia

Mehdi Mirza Mohammadi

Shih-Chieh Huang

Rishabh Kabra

Sebastien Henri Racaniere

Danilo Jiminez Rezende

A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.

Imagination-based agent neural networks

Methods, systems and apparatus, including computer programs encoded on computer storage media, for training a value neural network that is configured to receive an observation characterizing a state of an environment being interacted with by an agent and to process the observation in accordance with parameters of the value neural network to generate a value score. One of the systems performs operations that include training a supervised learning policy neural network; initializing initial values of parameters of a reinforcement learning policy neural network having a same architecture as the supervised learning policy network to the trained values of the parameters of the supervised learning policy neural network; training the reinforcement learning policy neural network on second training data; and training the value neural network to generate a value score for the state of the environment that represents a predicted long-term reward resulting from the environment being in the state.

Selecting actions to be performed by a reinforcement learning agent using tree search

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent interacting with an environment. One of the methods includes obtaining a representation of an observation; processing the representation using a convolutional long short-term memory (LSTM) neural network comprising a plurality of convolutional LSTM neural network layers; processing an action selection input comprising the final LSTM hidden state output for the time step using an action selection neural network that is configured to receive the action selection input and to process the action selection input to generate an action selection output that defines an action to be performed by the agent at the time step; selecting, from the action selection output, the action to be performed by the agent at the time step in accordance with an action selection policy; and causing the agent to perform the selected action.

Stacked convolutional long short-term memory for model-free reinforcement learning

Growing community of inventors

London, United Kingdom

Arthur Clement Guez