公开(公告)号：US20230252288A1

公开(公告)日：2023-08-10

申请号：US18131753

申请日：2023-04-06

申请人： DeepMind Technologies Limited

发明人： David Budden ,  Gabriel Barth-Maron ,  John Quan ,  Daniel George Horgan

IPC分类号： G06N3/08 ,  G06N20/00 ,  G06N3/088 ,  G06N3/04

CPC分类号： G06N3/08 ,  G06N20/00 ,  G06N3/088 ,  G06N3/04

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. One of the systems includes (i) a plurality of actor computing units, in which each of the actor computing units is configured to maintain a respective replica of the action selection neural network and to perform a plurality of actor operations, and (ii) one or more learner computing units, in which each of the one or more learner computing units is configured to perform a plurality of learner operations.

公开(公告)号：US11625604B2

公开(公告)日：2023-04-11

申请号：US16641751

申请日：2018-10-29

申请人： DeepMind Technologies Limited

发明人： David Budden ,  Gabriel Barth-Maron ,  John Quan ,  Daniel George Horgan

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06N3/088

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. One of the systems includes (i) a plurality of actor computing units, in which each of the actor computing units is configured to maintain a respective replica of the action selection neural network and to perform a plurality of actor operations, and (ii) one or more learner computing units, in which each of the one or more learner computing units is configured to perform a plurality of learner operations.

公开(公告)号：US20200265305A1

公开(公告)日：2020-08-20

申请号：US16641751

申请日：2018-10-29

申请人： DeepMind Technologies Limited

发明人： David Budden ,  Gabriel Barth-Maron ,  John Quan ,  Daniel George Horgan

IPC分类号： G06N3/08 ,  G06N20/00

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. One of the systems includes (i) a plurality of actor computing units, in which each of the actor computing units is configured to maintain a respective replica of the action selection neural network and to perform a plurality of actor operations, and (ii) one or more learner computing units, in which each of the one or more learner computing units is configured to perform a plurality of learner operations.