Deepmind Technologies Limited

Vinicius Zambaldi

Charles Blundell

Yujia Li

Adam Anthony Santoro

Peter William Battaglia

Victor Constant Bapst

Andrea Banino

Benigno Uria-Martínez

David Nunes Raposo

Hasuk Song

Andrea Tacchetti

Borja Ibarz Gabardos

A neural network system is proposed, including an input network for extracting, from state data, respective entity data for each a plurality of entities which are present, or at least potentially present, in the environment. The entity data describes the entity. The neural network contains a relational network for parsing this data, which includes one or more attention blocks which may be stacked to perform successive actions on the entity data. The attention blocks each include a respective transform network for each of the entities. The transform network for each entity is able to transform data which the transform network receives for the entity into modified entity data for the entity, based on data for a plurality of the other entities. An output network is arranged to receive data output by the relational network, and use the received data to select a respective action.

Reinforcement learning using a relational network for generating data encoding relationships between entities in an environment

Growing community of inventors

London, United Kingdom

Vinicius Zambaldi