DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS

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 th...

Full description

Saved in:
Bibliographic Details
Main Authors Dunning, Iain Robert, Czarnecki, Wojciech, Jaderberg, Maxwell Elliot
Format Patent
LanguageEnglish
Published 05.12.2019
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:Application Number: US201916425717