公开(公告)号：US20190279076A1

公开(公告)日：2019-09-12

申请号：US16298448

申请日：2019-03-11

Applicant: DeepMind Technologies Limited

Inventor： Huiyi Hu ,  Ray Jiang ,  Timothy Arthur Mann ,  Sven Adrian Gowal ,  Balaji Lakshminarayanan ,  Andras Gyorgy

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning from delayed outcomes using neural networks. One of the methods includes receiving an input observation; generating, from the input observation, an output label distribution over possible labels for the input observation at a final time, comprising: processing the input observation using a first neural network configured to process the input observation to generate a distribution over possible values for an intermediate indicator at a first time earlier than the final time; generating, from the distribution, an input value for the intermediate indicator; and processing the input value for the intermediate indicator using a second neural network configured to process the input value for the intermediate indicator to determine the output label distribution over possible values for the input observation at the final time; and providing an output derived from the output label distribution.