AGENT CONTROL USING TOKEN-BASED DYNAMICS MODELS
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using sequence-processing neural networks. In particular, the sequence-processing neural network is used as a dynamics model of the environment in order to perform planning when...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre |
| 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 | ZHANG, Jingwei SCHUBERT, Ingmar Fabian PARISOTTO, Emilio HEESS, Nicolas Manfred Otto BECHTLE, Sarah Maria Elisabeth HASENCLEVER, Leonard BYRAVAN, Arunkumar SPRINGENBERG, Jost Tobias |
| description | Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using sequence-processing neural networks. In particular, the sequence-processing neural network is used as a dynamics model of the environment in order to perform planning when selecting actions to be performed by an agent.
L'invention concerne des procédés, des systèmes et un appareil, y compris des programmes d'ordinateur codés sur un support de stockage d'ordinateur, pour commander des agents à l'aide de réseaux neuronaux de traitement de séquence. En particulier, le réseau neuronal de traitement de séquence est utilisé en tant que modèle dynamique de l'environnement afin d'effectuer une planification lors de la sélection d'actions à effectuer par un agent. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2024231311A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2024231311A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2024231311A13</originalsourceid><addsrcrecordid>eNrjZNB3dHf1C1Fw9vcLCfL3UQgN9vRzVwjx93b103VyDHZ1UXCJ9HP09XQOVvD1d3H1CeZhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfHh_kYGRiZGxobGhoaOhsbEqQIAmakmyw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>AGENT CONTROL USING TOKEN-BASED DYNAMICS MODELS</title><source>esp@cenet</source><creator>ZHANG, Jingwei ; SCHUBERT, Ingmar Fabian ; PARISOTTO, Emilio ; HEESS, Nicolas Manfred Otto ; BECHTLE, Sarah Maria Elisabeth ; HASENCLEVER, Leonard ; BYRAVAN, Arunkumar ; SPRINGENBERG, Jost Tobias</creator><creatorcontrib>ZHANG, Jingwei ; SCHUBERT, Ingmar Fabian ; PARISOTTO, Emilio ; HEESS, Nicolas Manfred Otto ; BECHTLE, Sarah Maria Elisabeth ; HASENCLEVER, Leonard ; BYRAVAN, Arunkumar ; SPRINGENBERG, Jost Tobias</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using sequence-processing neural networks. In particular, the sequence-processing neural network is used as a dynamics model of the environment in order to perform planning when selecting actions to be performed by an agent.
L'invention concerne des procédés, des systèmes et un appareil, y compris des programmes d'ordinateur codés sur un support de stockage d'ordinateur, pour commander des agents à l'aide de réseaux neuronaux de traitement de séquence. En particulier, le réseau neuronal de traitement de séquence est utilisé en tant que modèle dynamique de l'environnement afin d'effectuer une planification lors de la sélection d'actions à effectuer par un agent.</description><language>eng ; fre</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&date=20241114&DB=EPODOC&CC=WO&NR=2024231311A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25551,76302</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20241114&DB=EPODOC&CC=WO&NR=2024231311A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG, Jingwei</creatorcontrib><creatorcontrib>SCHUBERT, Ingmar Fabian</creatorcontrib><creatorcontrib>PARISOTTO, Emilio</creatorcontrib><creatorcontrib>HEESS, Nicolas Manfred Otto</creatorcontrib><creatorcontrib>BECHTLE, Sarah Maria Elisabeth</creatorcontrib><creatorcontrib>HASENCLEVER, Leonard</creatorcontrib><creatorcontrib>BYRAVAN, Arunkumar</creatorcontrib><creatorcontrib>SPRINGENBERG, Jost Tobias</creatorcontrib><title>AGENT CONTROL USING TOKEN-BASED DYNAMICS MODELS</title><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using sequence-processing neural networks. In particular, the sequence-processing neural network is used as a dynamics model of the environment in order to perform planning when selecting actions to be performed by an agent.
L'invention concerne des procédés, des systèmes et un appareil, y compris des programmes d'ordinateur codés sur un support de stockage d'ordinateur, pour commander des agents à l'aide de réseaux neuronaux de traitement de séquence. En particulier, le réseau neuronal de traitement de séquence est utilisé en tant que modèle dynamique de l'environnement afin d'effectuer une planification lors de la sélection d'actions à effectuer par un agent.</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>eNrjZNB3dHf1C1Fw9vcLCfL3UQgN9vRzVwjx93b103VyDHZ1UXCJ9HP09XQOVvD1d3H1CeZhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfHh_kYGRiZGxobGhoaOhsbEqQIAmakmyw</recordid><startdate>20241114</startdate><enddate>20241114</enddate><creator>ZHANG, Jingwei</creator><creator>SCHUBERT, Ingmar Fabian</creator><creator>PARISOTTO, Emilio</creator><creator>HEESS, Nicolas Manfred Otto</creator><creator>BECHTLE, Sarah Maria Elisabeth</creator><creator>HASENCLEVER, Leonard</creator><creator>BYRAVAN, Arunkumar</creator><creator>SPRINGENBERG, Jost Tobias</creator><scope>EVB</scope></search><sort><creationdate>20241114</creationdate><title>AGENT CONTROL USING TOKEN-BASED DYNAMICS MODELS</title><author>ZHANG, Jingwei ; SCHUBERT, Ingmar Fabian ; PARISOTTO, Emilio ; HEESS, Nicolas Manfred Otto ; BECHTLE, Sarah Maria Elisabeth ; HASENCLEVER, Leonard ; BYRAVAN, Arunkumar ; SPRINGENBERG, Jost Tobias</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2024231311A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre</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>ZHANG, Jingwei</creatorcontrib><creatorcontrib>SCHUBERT, Ingmar Fabian</creatorcontrib><creatorcontrib>PARISOTTO, Emilio</creatorcontrib><creatorcontrib>HEESS, Nicolas Manfred Otto</creatorcontrib><creatorcontrib>BECHTLE, Sarah Maria Elisabeth</creatorcontrib><creatorcontrib>HASENCLEVER, Leonard</creatorcontrib><creatorcontrib>BYRAVAN, Arunkumar</creatorcontrib><creatorcontrib>SPRINGENBERG, Jost Tobias</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG, Jingwei</au><au>SCHUBERT, Ingmar Fabian</au><au>PARISOTTO, Emilio</au><au>HEESS, Nicolas Manfred Otto</au><au>BECHTLE, Sarah Maria Elisabeth</au><au>HASENCLEVER, Leonard</au><au>BYRAVAN, Arunkumar</au><au>SPRINGENBERG, Jost Tobias</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>AGENT CONTROL USING TOKEN-BASED DYNAMICS MODELS</title><date>2024-11-14</date><risdate>2024</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using sequence-processing neural networks. In particular, the sequence-processing neural network is used as a dynamics model of the environment in order to perform planning when selecting actions to be performed by an agent.
L'invention concerne des procédés, des systèmes et un appareil, y compris des programmes d'ordinateur codés sur un support de stockage d'ordinateur, pour commander des agents à l'aide de réseaux neuronaux de traitement de séquence. En particulier, le réseau neuronal de traitement de séquence est utilisé en tant que modèle dynamique de l'environnement afin d'effectuer une planification lors de la sélection d'actions à effectuer par un agent.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre |
| recordid | cdi_epo_espacenet_WO2024231311A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | AGENT CONTROL USING TOKEN-BASED DYNAMICS MODELS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T20%3A22%3A43IST&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=ZHANG,%20Jingwei&rft.date=2024-11-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2024231311A1%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 |