Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural networks

Invention Grant

US11842261B2 Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural networks 有权

Please log in to see more content

Patent Title: Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural networks
Application No.: US17121679

Application Date: 2020-12-14
Publication No.: US11842261B2

Publication Date: 2023-12-12
Inventor: Iain Robert Dunning , Wojciech Czarnecki , Maxwell Elliot Jaderberg
Applicant: DeepMind Technologies Limited
Applicant Address: GB London
Assignee: DeepMind Technologies Limited
Current Assignee: DeepMind Technologies Limited
Current Assignee Address: GB London
Agency: Fish & Richardson P.C.
Main IPC: G06N3/045
IPC: G06N3/045 ; G06N3/08 ; G06N3/047 ; G06F17/18

Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural networks

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.

Public/Granted literature

US20210097373A1 DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS Public/Granted day:2021-04-01

Information query

Espacenet