ASYNCHRONOUS DEEP REINFORCEMENT LEARNING

ASYNCHRONOUS DEEP REINFORCEMENT LEARNING

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes one or more computers configured to implement a plurality of workers, wherein each worker is configured to operate independently o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HARLEY, Timothy James Alexander, KAVUKCUOGLU, Koray, BADIA, Adria Puigdomenech, SILVER, David, MNIH, Volodymyr, GRAVES, Alexander Benjamin
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator HARLEY, Timothy James Alexander
KAVUKCUOGLU, Koray
BADIA, Adria Puigdomenech
SILVER, David
MNIH, Volodymyr
GRAVES, Alexander Benjamin
description Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes one or more computers configured to implement a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network. Aspects of the present specification have the technical effect of faster training of a neural network and/or reducing the memory requirements for the training.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4398159A2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4398159A2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4398159A23</originalsourceid><addsrcrecordid>eNrjZNBwDI70c_YI8vfzDw1WcHF1DVAIcvX0c_MPcnb1dfULUfBxdQzy8_Rz52FgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8a4BJsaWFoamlo5GxkQoAQDlsCQS</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ASYNCHRONOUS DEEP REINFORCEMENT LEARNING</title><source>esp@cenet</source><creator>HARLEY, Timothy James Alexander ; KAVUKCUOGLU, Koray ; BADIA, Adria Puigdomenech ; SILVER, David ; MNIH, Volodymyr ; GRAVES, Alexander Benjamin</creator><creatorcontrib>HARLEY, Timothy James Alexander ; KAVUKCUOGLU, Koray ; BADIA, Adria Puigdomenech ; SILVER, David ; MNIH, Volodymyr ; GRAVES, Alexander Benjamin</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes one or more computers configured to implement a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network. Aspects of the present specification have the technical effect of faster training of a neural network and/or reducing the memory requirements for the training.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240710&amp;DB=EPODOC&amp;CC=EP&amp;NR=4398159A2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240710&amp;DB=EPODOC&amp;CC=EP&amp;NR=4398159A2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HARLEY, Timothy James Alexander</creatorcontrib><creatorcontrib>KAVUKCUOGLU, Koray</creatorcontrib><creatorcontrib>BADIA, Adria Puigdomenech</creatorcontrib><creatorcontrib>SILVER, David</creatorcontrib><creatorcontrib>MNIH, Volodymyr</creatorcontrib><creatorcontrib>GRAVES, Alexander Benjamin</creatorcontrib><title>ASYNCHRONOUS DEEP REINFORCEMENT LEARNING</title><description>Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes one or more computers configured to implement a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network. Aspects of the present specification have the technical effect of faster training of a neural network and/or reducing the memory requirements for the training.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNBwDI70c_YI8vfzDw1WcHF1DVAIcvX0c_MPcnb1dfULUfBxdQzy8_Rz52FgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8a4BJsaWFoamlo5GxkQoAQDlsCQS</recordid><startdate>20240710</startdate><enddate>20240710</enddate><creator>HARLEY, Timothy James Alexander</creator><creator>KAVUKCUOGLU, Koray</creator><creator>BADIA, Adria Puigdomenech</creator><creator>SILVER, David</creator><creator>MNIH, Volodymyr</creator><creator>GRAVES, Alexander Benjamin</creator><scope>EVB</scope></search><sort><creationdate>20240710</creationdate><title>ASYNCHRONOUS DEEP REINFORCEMENT LEARNING</title><author>HARLEY, Timothy James Alexander ; KAVUKCUOGLU, Koray ; BADIA, Adria Puigdomenech ; SILVER, David ; MNIH, Volodymyr ; GRAVES, Alexander Benjamin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4398159A23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HARLEY, Timothy James Alexander</creatorcontrib><creatorcontrib>KAVUKCUOGLU, Koray</creatorcontrib><creatorcontrib>BADIA, Adria Puigdomenech</creatorcontrib><creatorcontrib>SILVER, David</creatorcontrib><creatorcontrib>MNIH, Volodymyr</creatorcontrib><creatorcontrib>GRAVES, Alexander Benjamin</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HARLEY, Timothy James Alexander</au><au>KAVUKCUOGLU, Koray</au><au>BADIA, Adria Puigdomenech</au><au>SILVER, David</au><au>MNIH, Volodymyr</au><au>GRAVES, Alexander Benjamin</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ASYNCHRONOUS DEEP REINFORCEMENT LEARNING</title><date>2024-07-10</date><risdate>2024</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes one or more computers configured to implement a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network. Aspects of the present specification have the technical effect of faster training of a neural network and/or reducing the memory requirements for the training.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4398159A2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title ASYNCHRONOUS DEEP REINFORCEMENT LEARNING
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T18%3A48%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=HARLEY,%20Timothy%20James%20Alexander&rft.date=2024-07-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4398159A2%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true