公开(公告)号：US20210201156A1

公开(公告)日：2021-07-01

申请号：US17056640

申请日：2019-05-20

Applicant: GOOGLE LLC

Inventor： Danijar Hafner ,  Jacob Buckman ,  Honglak Lee ,  Eugene Brevdo ,  George Jay Tucker

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sample-efficient reinforcement learning. One of the methods includes maintaining an ensemble of Q networks, an ensemble of transition models, and an ensemble of reward models; obtaining a transition; generating, using the ensemble of transition models, M trajectories; for each time step in each of the trajectories: generating, using the ensemble of reward models, N rewards for the time step, generating, using the ensemble of Q networks, L Q values for the time step, and determining, from the rewards, the Q values, and the training reward, L*N candidate target Q values for the trajectory and for the time step; for each of the time steps, combining the candidate target Q values; determining a final target Q value; and training at least one of the Q networks in the ensemble using the final target Q value.

公开(公告)号：US11354574B2

公开(公告)日：2022-06-07

申请号：US16859789

申请日：2020-04-27

Applicant: Google LLC

Inventor： Aurko Roy ,  Ian Goodfellow ,  Jacob Buckman ,  Colin Abraham Raffel

IPC: G06N3/08 ,  G06F17/16 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for increasing the security of neural network by discretizing neural network inputs. One of the methods includes receiving a network input for a neural network; processing the network input using a discretization layer, wherein the discretization layer is configured to generate a discretized network input comprising a respective discretized vector for each of the numeric values in the network input; and processing the discretized network input using the plurality of additional neural network layers to generate a network output for the network input.

公开(公告)号：US20200257978A1

公开(公告)日：2020-08-13

申请号：US16859789

申请日：2020-04-27

Applicant: Google LLC

Inventor： Aurko Roy ,  Ian Goodfellow ,  Jacob Buckman ,  Colin Abraham Raffel

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for increasing the security of neural network by discretizing neural network inputs. One of the methods includes receiving a network input for a neural network; processing the network input using a discretization layer, wherein the discretization layer is configured to generate a discretized network input comprising a respective discretized vector for each of the numeric values in the network input; and processing the discretized network input using the plurality of additional neural network layers to generate a network output for the network input.