公开(公告)号：US20180032864A1

公开(公告)日：2018-02-01

申请号：US15280784

申请日：2016-09-29

Applicant: Google Inc.

Inventor： Thore Kurt Hartwig Graepel ,  Shih-Chieh Huang ,  David Silver ,  Arthur Clement Guez ,  Laurent Sifre ,  Ilya Sutskever ,  Christopher Maddison

IPC: G06N3/08 ,  G06F17/30

CPC classification number: G06N3/08 ,  G06F16/9027 ,  G06N3/0427 ,  G06N3/0454 ,  G06N5/003 ,  G16B40/00 ,  G16H50/20

Abstract: 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.

公开(公告)号：US20180032863A1

公开(公告)日：2018-02-01

申请号：US15280711

申请日：2016-09-29

Applicant: Google Inc.

Inventor： Thore Kurt Hartwig Graepel ,  Shih-Chieh Huang ,  David Silver ,  Arthur Clement Guez ,  Laurent Sifre ,  Ilya Sutskever ,  Christopher Maddison

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G05B13/027 ,  G06N3/04 ,  G06N3/0427 ,  G06N3/0454 ,  G16B40/00 ,  G16H50/20

Abstract: 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.