公开(公告)号：US20230244452A1

公开(公告)日：2023-08-03

申请号：US18105211

申请日：2023-02-02

Applicant: DeepMind Technologies Limited

Inventor： Yujia Li ,  David Hugo Choi ,  Junyoung Chung ,  Nathaniel Arthur Kushman ,  Julian Schrittwieser ,  Rémi Leblond ,  Thomas Edward Eccles ,  James Thomas Keeling ,  Felix Axel Gimeno Gil ,  Agustín Matías Dal Lago ,  Thomas Keisuke Hubert ,  Peter Choy ,  Cyprien de Masson d'Autume ,  Esme Sutherland Robson ,  Oriol Vinyals

IPC: G06F8/30

CPC classification number: G06F8/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating computer code using neural networks. One of the methods includes receiving description data describing a computer programming task; receiving a first set of inputs for the computer programming task; generating a plurality of candidate computer programs by sampling a plurality of output sequences from a set of one or more generative neural networks; for each candidate computer program in a subset of the candidate computer programs and for each input in the first set: executing the candidate computer program on the input to generate an output; and selecting, from the candidate computer programs, one or more computer programs as synthesized computer programs for performing the computer programming task based at least in part on the outputs generated by executing the candidate computer programs in the subset on the inputs in the first set of inputs.

公开(公告)号：US20220374683A1

公开(公告)日：2022-11-24

申请号：US17668050

申请日：2022-02-09

Applicant: DeepMind Technologies Limited

Inventor： Thomas Edward Eccles ,  Ian Michael Gemp ,  János Kramár ,  Marta Garnelo Abellanas ,  Dan Rosenbaum ,  Yoram Bachrach ,  Thore Kurt Hartwig Graepel

IPC: G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting an optimal feature point in a continuous domain for a group of agents. A computer-implemented system obtains, for each of a plurality of agents, respective training data that comprises a respective utility score for each of a plurality of discrete points in the continuous domain. The system trains, for each of the plurality of agents and on the respective training data for the agents, a respective neural network that is configured to receive an input comprising a point in the continuous domain and to generate as output a predicted utility score for the agent at the point. And the system identifies the optimal point by optimizing an approximation of the shared outcome function that is defined by, for any given point in the continuous domain, a combination of the predicted utility scores generated by the respective neural networks for each of the plurality of agents by processing an input comprising the given point.