公开(公告)号：US20230101930A1

公开(公告)日：2023-03-30

申请号：US17794780

申请日：2021-02-08

Applicant: DeepMind Technologies Limited

Inventor： Samuel Ritter ,  Ryan Faulkner ,  David Nunes Raposo

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment to accomplish a goal. In one aspect, a method comprises: generating a respective planning embedding corresponding to each of multiple experience tuples in an external memory, wherein each experience tuple characterizes interaction of the agent with the environment at a respective previous time step; processing the planning embeddings using a planning neural network to generate an implicit plan for accomplishing the goal; and selecting the action to be performed by the agent at the time step using the implicit plan.

公开(公告)号：US20210081795A1

公开(公告)日：2021-03-18

申请号：US17107621

申请日：2020-11-30

Applicant: DeepMind Technologies Limited

Inventor： Mike Chrzanowski ,  Jack William Rae ,  Ryan Faulkner ,  Theophane Guillaume Weber ,  David Nunes Raposo ,  Adam Anthony Santoro

IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.

公开(公告)号：US10853725B2

公开(公告)日：2020-12-01

申请号：US16415954

申请日：2019-05-17

Applicant: DeepMind Technologies Limited

Inventor： Mike Chrzanowski ,  Jack William Rae ,  Ryan Faulkner ,  Theophane Guillaume Weber ,  David Nunes Raposo ,  Adam Anthony Santoro

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.

公开(公告)号：US11836596B2

公开(公告)日：2023-12-05

申请号：US17107621

申请日：2020-11-30

Applicant: DeepMind Technologies Limited

Inventor： Mike Chrzanowski ,  Jack William Rae ,  Ryan Faulkner ,  Theophane Guillaume Weber ,  David Nunes Raposo ,  Adam Anthony Santoro

IPC: G06N3/08 ,  G06N3/042 ,  G06N3/04 ,  G06N20/00 ,  G06F18/2413

CPC classification number: G06N3/042 ,  G06F18/24137 ,  G06N3/04 ,  G06N3/08 ,  G06N20/00

Abstract: A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.