公开(公告)号：US11250475B2

公开(公告)日：2022-02-15

申请号：US16918805

申请日：2020-07-01

Applicant: DeepMind Technologies Limited

Inventor： Andrea Tacchetti ,  Daniel Joseph Strouse ,  Marta Garnelo Abellanas ,  Thore Kurt Hartwig Graepel ,  Yoram Bachrach

IPC: G06Q30/02 ,  G06N3/04 ,  G06N3/02 ,  G10L25/30 ,  G06K9/28

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for efficiently allocating resources among participants. Methods can include receiving valuation data specifying, for each of a plurality of entities, a respective valuation for each of a plurality of resource subsets, each resource subset comprising a different combination of one or more resources of a plurality of resources. After receiving valuation data, assigning each resource in the plurality of resources to a respective entity of the plurality of entities based on the valuations and generating, for each particular entity, a respective input representation that is derived from valuations of every other entity in the plurality of entities other than the particular entity. The input representation for each particular entity is processed using a neural network to generate a rule for the particular entity and a payment based on the rule output for the entities.

公开(公告)号：US20220005079A1

公开(公告)日：2022-01-06

申请号：US16918805

申请日：2020-07-01

Applicant: DeepMind Technologies Limited

Inventor： Andrea Tacchetti ,  Daniel Joseph Strouse ,  Marta Garnelo Abellanas ,  Thore Kurt Hartwig Graepel ,  Yoram Bachrach

IPC: G06Q30/02 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for efficiently allocating resources among participants. Methods can include receiving valuation data specifying, for each of a plurality of entities, a respective valuation for each of a plurality of resource subsets, each resource subset comprising a different combination of one or more resources of a plurality of resources. After receiving valuation data, assigning each resource in the plurality of resources to a respective entity of the plurality of entities based on the valuations and generating, for each particular entity, a respective input representation that is derived from valuations of every other entity in the plurality of entities other than the particular entity. The input representation for each particular entity is processed using a neural network to generate a rule for the particular entity and a payment based on the rule output for the entities.

公开(公告)号：US20210192358A1

公开(公告)日：2021-06-24

申请号：US17054632

申请日：2019-05-20

Applicant: DeepMind Technologies Limited

Inventor： Hasuk Song ,  Andrea Tacchetti ,  Peter William Battaglia ,  Vinicius Zambaldi

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting the actions of, or influences on, agents in environments with multiple agents, in particular for reinforcement learning. In one aspect, a relational forward model (RFM) system receives agent data representing agent actions for each of multiple agents and implements: an encoder graph neural network subsystem to process the agent data as graph data to provide encoded graph data, a recurrent graph neural network subsystem to process the encoded graph data to provide processed graph data, a decoder graph neural network subsystem to decode the processed graph data to provide decoded graph data and an output to provide representation data for node and/or edge attributes of the decoded graph data relating to a predicted action of one or more of the agents. A reinforcement learning system includes the RFM system.