公开(公告)号：US20240345873A1

公开(公告)日：2024-10-17

申请号：US18294784

申请日：2022-08-03

申请人： DeepMind Technologies Limited

发明人： Tom Schaul ,  Miruna Pîslar

IPC分类号： G06F9/48

CPC分类号： G06F9/4875

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an agent can be controlled to perform a task episode by switching the control policy that is used to control the agent at one or more time steps during the task episode.

公开(公告)号：US20240104353A1

公开(公告)日：2024-03-28

申请号：US18274748

申请日：2022-02-08

申请人： DeepMind Technologies Limited

发明人： Rémi Bertrand Francis Leblond ,  Jean-Baptiste Alayrac ,  Laurent Sifre ,  Miruna Pîslar ,  Jean-Baptiste Lespiau ,  Ioannis Antonoglou ,  Karen Simonyan ,  David Silver ,  Oriol Vinyals

IPC分类号： G06N3/0455

CPC分类号： G06N3/0455

摘要： A computer-implemented method for generating an output token sequence from an input token sequence. The method combines a look ahead tree search, such as a Monte Carlo tree search, with a sequence-to-sequence neural network system. The sequence-to-sequence neural network system has a policy output defining a next token probability distribution, and may include a value neural network providing a value output to evaluate a sequence. An initial partial output sequence is extended using the look ahead tree search guided by the policy output and, in implementations, the value output, of the sequence-to-sequence neural network system until a complete output sequence is obtained.