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 agentusing both a slow updating recurrent neural network and a fast updating recurrent neural network tha...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| 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 | DUNNING IAIN ROBERT JADERBERG MAXWELL ELLIOT CZARNECKI WOJCIECH |
| description | 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 agentusing 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.
用于强化学习的方法、系统和装置，包括编码在计算机存储介质上的计算机程序。方法之一包括使用慢速更新循环神经网络和快速更新循环神经网络两者来选择要由代理执行的动作，该快速更新循环神经网络接收包括慢速更新循环神经网络的隐藏状态的快速更新输入。 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN112119406A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN112119406A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN112119406A3</originalsourceid><addsrcrecordid>eNqNykEKwjAQQNFuXIh6h_EAglERXIZkYoNxUiYJWZYicSVaaO-PFjxAVx8-b1mNGrEBRkvGs8I7UgSHksnSFbKNNRgZIqRGyzgtRpWYJ0WYWLpfYvZ8CyBJQ3A-z7DravHsXkPZ_Luqtgajqnel_7Rl6LtHeZexVSTEQYjLaX-WxznmCwYdOYI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS</title><source>esp@cenet</source><creator>DUNNING IAIN ROBERT ; JADERBERG MAXWELL ELLIOT ; CZARNECKI WOJCIECH</creator><creatorcontrib>DUNNING IAIN ROBERT ; JADERBERG MAXWELL ELLIOT ; CZARNECKI WOJCIECH</creatorcontrib><description>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 agentusing 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.
用于强化学习的方法、系统和装置，包括编码在计算机存储介质上的计算机程序。方法之一包括使用慢速更新循环神经网络和快速更新循环神经网络两者来选择要由代理执行的动作，该快速更新循环神经网络接收包括慢速更新循环神经网络的隐藏状态的快速更新输入。</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2020</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&date=20201222&DB=EPODOC&CC=CN&NR=112119406A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201222&DB=EPODOC&CC=CN&NR=112119406A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DUNNING IAIN ROBERT</creatorcontrib><creatorcontrib>JADERBERG MAXWELL ELLIOT</creatorcontrib><creatorcontrib>CZARNECKI WOJCIECH</creatorcontrib><title>DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS</title><description>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 agentusing 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.
用于强化学习的方法、系统和装置，包括编码在计算机存储介质上的计算机程序。方法之一包括使用慢速更新循环神经网络和快速更新循环神经网络两者来选择要由代理执行的动作，该快速更新循环神经网络接收包括慢速更新循环神经网络的隐藏状态的快速更新输入。</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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNykEKwjAQQNFuXIh6h_EAglERXIZkYoNxUiYJWZYicSVaaO-PFjxAVx8-b1mNGrEBRkvGs8I7UgSHksnSFbKNNRgZIqRGyzgtRpWYJ0WYWLpfYvZ8CyBJQ3A-z7DravHsXkPZ_Luqtgajqnel_7Rl6LtHeZexVSTEQYjLaX-WxznmCwYdOYI</recordid><startdate>20201222</startdate><enddate>20201222</enddate><creator>DUNNING IAIN ROBERT</creator><creator>JADERBERG MAXWELL ELLIOT</creator><creator>CZARNECKI WOJCIECH</creator><scope>EVB</scope></search><sort><creationdate>20201222</creationdate><title>DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS</title><author>DUNNING IAIN ROBERT ; JADERBERG MAXWELL ELLIOT ; CZARNECKI WOJCIECH</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN112119406A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</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>DUNNING IAIN ROBERT</creatorcontrib><creatorcontrib>JADERBERG MAXWELL ELLIOT</creatorcontrib><creatorcontrib>CZARNECKI WOJCIECH</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DUNNING IAIN ROBERT</au><au>JADERBERG MAXWELL ELLIOT</au><au>CZARNECKI WOJCIECH</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS</title><date>2020-12-22</date><risdate>2020</risdate><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 agentusing 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.
用于强化学习的方法、系统和装置，包括编码在计算机存储介质上的计算机程序。方法之一包括使用慢速更新循环神经网络和快速更新循环神经网络两者来选择要由代理执行的动作，该快速更新循环神经网络接收包括慢速更新循环神经网络的隐藏状态的快速更新输入。</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN112119406A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T16%3A34%3A25IST&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=DUNNING%20IAIN%20ROBERT&rft.date=2020-12-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN112119406A%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 |