SELECTING ACTIONS USING MULTI-MODAL INPUTS
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system includes a language encoder model that is configured to receive a text string in a particular...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre ; ger |
| 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 | BLUNSOM, Philip HILL, Felix George HERMANN, Karl Moritz |
| description | Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system includes a language encoder model that is configured to receive a text string in a particular natural language, and process the text string to generate a text embedding of the text string. The system includes an observation encoder neural network that is configured to receive an observation characterizing a state of the environment, and process the observation to generate an observation embedding of the observation. The system includes a subsystem that is configured to obtain a current text embedding of a current text string and a current observation embedding of a current observation. The subsystem is configured to select an action to be performed by the agent in response to the current observation. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4273757A3</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4273757A3</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4273757A33</originalsourceid><addsrcrecordid>eNrjZNAKdvVxdQ7x9HNXcARS_n7BCqHBIJ5vqE-Ip66vv4ujj4KnX0BoSDAPA2taYk5xKi-U5mZQcHMNcfbQTS3Ij08tLkhMTs1LLYl3DTAxMjc2NzV3NDYmQgkAHlckgA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SELECTING ACTIONS USING MULTI-MODAL INPUTS</title><source>esp@cenet</source><creator>BLUNSOM, Philip ; HILL, Felix George ; HERMANN, Karl Moritz</creator><creatorcontrib>BLUNSOM, Philip ; HILL, Felix George ; HERMANN, Karl Moritz</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system includes a language encoder model that is configured to receive a text string in a particular natural language, and process the text string to generate a text embedding of the text string. The system includes an observation encoder neural network that is configured to receive an observation characterizing a state of the environment, and process the observation to generate an observation embedding of the observation. The system includes a subsystem that is configured to obtain a current text embedding of a current text string and a current observation embedding of a current observation. The subsystem is configured to select an action to be performed by the agent in response to the current observation.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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=20240214&DB=EPODOC&CC=EP&NR=4273757A3$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240214&DB=EPODOC&CC=EP&NR=4273757A3$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>BLUNSOM, Philip</creatorcontrib><creatorcontrib>HILL, Felix George</creatorcontrib><creatorcontrib>HERMANN, Karl Moritz</creatorcontrib><title>SELECTING ACTIONS USING MULTI-MODAL INPUTS</title><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system includes a language encoder model that is configured to receive a text string in a particular natural language, and process the text string to generate a text embedding of the text string. The system includes an observation encoder neural network that is configured to receive an observation characterizing a state of the environment, and process the observation to generate an observation embedding of the observation. The system includes a subsystem that is configured to obtain a current text embedding of a current text string and a current observation embedding of a current observation. The subsystem is configured to select an action to be performed by the agent in response to the current observation.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAKdvVxdQ7x9HNXcARS_n7BCqHBIJ5vqE-Ip66vv4ujj4KnX0BoSDAPA2taYk5xKi-U5mZQcHMNcfbQTS3Ij08tLkhMTs1LLYl3DTAxMjc2NzV3NDYmQgkAHlckgA</recordid><startdate>20240214</startdate><enddate>20240214</enddate><creator>BLUNSOM, Philip</creator><creator>HILL, Felix George</creator><creator>HERMANN, Karl Moritz</creator><scope>EVB</scope></search><sort><creationdate>20240214</creationdate><title>SELECTING ACTIONS USING MULTI-MODAL INPUTS</title><author>BLUNSOM, Philip ; HILL, Felix George ; HERMANN, Karl Moritz</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4273757A33</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>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>BLUNSOM, Philip</creatorcontrib><creatorcontrib>HILL, Felix George</creatorcontrib><creatorcontrib>HERMANN, Karl Moritz</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>BLUNSOM, Philip</au><au>HILL, Felix George</au><au>HERMANN, Karl Moritz</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SELECTING ACTIONS USING MULTI-MODAL INPUTS</title><date>2024-02-14</date><risdate>2024</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system includes a language encoder model that is configured to receive a text string in a particular natural language, and process the text string to generate a text embedding of the text string. The system includes an observation encoder neural network that is configured to receive an observation characterizing a state of the environment, and process the observation to generate an observation embedding of the observation. The system includes a subsystem that is configured to obtain a current text embedding of a current text string and a current observation embedding of a current observation. The subsystem is configured to select an action to be performed by the agent in response to the current observation.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre ; ger |
| recordid | cdi_epo_espacenet_EP4273757A3 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | SELECTING ACTIONS USING MULTI-MODAL INPUTS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T20%3A46%3A55IST&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=BLUNSOM,%20Philip&rft.date=2024-02-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4273757A3%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 |