REINFORCEMENT AND IMITATION LEARNING FOR A TASK

A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated f...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Merel, Joshua, Heess, Nicolas Manfred Otto, Tunyasuvunakool, Saran, Kramár, János, Zhu, Yuke, Wang, Ziyu
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING CHAMBERS PROVIDED WITH MANIPULATION DEVICES COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HAND TOOLS MANIPULATORS PERFORMING OPERATIONS PHYSICS PORTABLE POWER-DRIVEN TOOLS TRANSPORTING
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	Merel, Joshua Heess, Nicolas Manfred Otto Tunyasuvunakool, Saran Kramár, János Zhu, Yuke Wang, Ziyu
description	A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023330848A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023330848A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023330848A13</originalsourceid><addsrcrecordid>eNrjZNAPcvX0c_MPcnb1dfULUXD0c1Hw9PUMcQzx9PdT8HF1DPLz9HNXACpQcFQIcQz25mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGxsbGBhYmFo6GxsSpAgCS6ibJ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>REINFORCEMENT AND IMITATION LEARNING FOR A TASK</title><source>esp@cenet</source><creator>Merel, Joshua ; Heess, Nicolas Manfred Otto ; Tunyasuvunakool, Saran ; Kramár, János ; Zhu, Yuke ; Wang, Ziyu</creator><creatorcontrib>Merel, Joshua ; Heess, Nicolas Manfred Otto ; Tunyasuvunakool, Saran ; Kramár, János ; Zhu, Yuke ; Wang, Ziyu</creatorcontrib><description>A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.</description><language>eng</language><subject>CALCULATING ; CHAMBERS PROVIDED WITH MANIPULATION DEVICES ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HAND TOOLS ; MANIPULATORS ; PERFORMING OPERATIONS ; PHYSICS ; PORTABLE POWER-DRIVEN TOOLS ; TRANSPORTING</subject><creationdate>2023</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=20231019&DB=EPODOC&CC=US&NR=2023330848A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231019&DB=EPODOC&CC=US&NR=2023330848A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Merel, Joshua</creatorcontrib><creatorcontrib>Heess, Nicolas Manfred Otto</creatorcontrib><creatorcontrib>Tunyasuvunakool, Saran</creatorcontrib><creatorcontrib>Kramár, János</creatorcontrib><creatorcontrib>Zhu, Yuke</creatorcontrib><creatorcontrib>Wang, Ziyu</creatorcontrib><title>REINFORCEMENT AND IMITATION LEARNING FOR A TASK</title><description>A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.</description><subject>CALCULATING</subject><subject>CHAMBERS PROVIDED WITH MANIPULATION DEVICES</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HAND TOOLS</subject><subject>MANIPULATORS</subject><subject>PERFORMING OPERATIONS</subject><subject>PHYSICS</subject><subject>PORTABLE POWER-DRIVEN TOOLS</subject><subject>TRANSPORTING</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAPcvX0c_MPcnb1dfULUXD0c1Hw9PUMcQzx9PdT8HF1DPLz9HNXACpQcFQIcQz25mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGxsbGBhYmFo6GxsSpAgCS6ibJ</recordid><startdate>20231019</startdate><enddate>20231019</enddate><creator>Merel, Joshua</creator><creator>Heess, Nicolas Manfred Otto</creator><creator>Tunyasuvunakool, Saran</creator><creator>Kramár, János</creator><creator>Zhu, Yuke</creator><creator>Wang, Ziyu</creator><scope>EVB</scope></search><sort><creationdate>20231019</creationdate><title>REINFORCEMENT AND IMITATION LEARNING FOR A TASK</title><author>Merel, Joshua ; Heess, Nicolas Manfred Otto ; Tunyasuvunakool, Saran ; Kramár, János ; Zhu, Yuke ; Wang, Ziyu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023330848A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>CHAMBERS PROVIDED WITH MANIPULATION DEVICES</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HAND TOOLS</topic><topic>MANIPULATORS</topic><topic>PERFORMING OPERATIONS</topic><topic>PHYSICS</topic><topic>PORTABLE POWER-DRIVEN TOOLS</topic><topic>TRANSPORTING</topic><toplevel>online_resources</toplevel><creatorcontrib>Merel, Joshua</creatorcontrib><creatorcontrib>Heess, Nicolas Manfred Otto</creatorcontrib><creatorcontrib>Tunyasuvunakool, Saran</creatorcontrib><creatorcontrib>Kramár, János</creatorcontrib><creatorcontrib>Zhu, Yuke</creatorcontrib><creatorcontrib>Wang, Ziyu</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Merel, Joshua</au><au>Heess, Nicolas Manfred Otto</au><au>Tunyasuvunakool, Saran</au><au>Kramár, János</au><au>Zhu, Yuke</au><au>Wang, Ziyu</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>REINFORCEMENT AND IMITATION LEARNING FOR A TASK</title><date>2023-10-19</date><risdate>2023</risdate><abstract>A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2023330848A1
source	esp@cenet
subjects	CALCULATING CHAMBERS PROVIDED WITH MANIPULATION DEVICES COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HAND TOOLS MANIPULATORS PERFORMING OPERATIONS PHYSICS PORTABLE POWER-DRIVEN TOOLS TRANSPORTING
title	REINFORCEMENT AND IMITATION LEARNING FOR A TASK
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T15%3A44%3A13IST&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=Merel,%20Joshua&rft.date=2023-10-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023330848A1%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