Modular reinforcement learning model processing method, system and equipment and storage medium

The invention relates to a modular reinforcement learning model processing method and device, computer equipment and a storage medium. The method comprises that: interaction data generated by a virtual object in an interaction process with an interaction environment is obtained; the virtual object i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG ZHENGSHENG, LIU YONGSHENG, ZHOU ZHENG, ZHU HENGMAN
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 ZHANG ZHENGSHENG
LIU YONGSHENG
ZHOU ZHENG
ZHU HENGMAN
description The invention relates to a modular reinforcement learning model processing method and device, computer equipment and a storage medium. The method comprises that: interaction data generated by a virtual object in an interaction process with an interaction environment is obtained; the virtual object is controlled by a running component in a reinforcement learning system deployed in the cloud; the reinforcement learning system further comprises a learning assembly and an evaluation assembly; the reinforcement learning model is iteratively trained based on the interaction data through a learning component; in the iterative training process, the reinforcement learning model obtained through iterative training is evaluated through an evaluation component, and whether the reinforcement learning model obtained through iterative training meets interaction conditions or not is judged according to a result obtained through evaluation; and if not, the model associated with the running component is updated according to th
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN112862108A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN112862108A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN112862108A3</originalsourceid><addsrcrecordid>eNqNi7EKwjAURbs4iPoPz13BVJCuUhQXndxLaG5rIMmLecng36vFD3C6nMO586q7silOJ0qwYeDUwyNkctAp2DCSZwNHMXEPkUkgP9hsSF6S4UkHQ3gWG6fblyRz0iM-obHFL6vZoJ1g9dtFtT6f7u1li8gdJOoeAblrb0rVzaFWu-a4_6d5A-AAPYk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Modular reinforcement learning model processing method, system and equipment and storage medium</title><source>esp@cenet</source><creator>ZHANG ZHENGSHENG ; LIU YONGSHENG ; ZHOU ZHENG ; ZHU HENGMAN</creator><creatorcontrib>ZHANG ZHENGSHENG ; LIU YONGSHENG ; ZHOU ZHENG ; ZHU HENGMAN</creatorcontrib><description>The invention relates to a modular reinforcement learning model processing method and device, computer equipment and a storage medium. The method comprises that: interaction data generated by a virtual object in an interaction process with an interaction environment is obtained; the virtual object is controlled by a running component in a reinforcement learning system deployed in the cloud; the reinforcement learning system further comprises a learning assembly and an evaluation assembly; the reinforcement learning model is iteratively trained based on the interaction data through a learning component; in the iterative training process, the reinforcement learning model obtained through iterative training is evaluated through an evaluation component, and whether the reinforcement learning model obtained through iterative training meets interaction conditions or not is judged according to a result obtained through evaluation; and if not, the model associated with the running component is updated according to th</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2021</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=20210528&amp;DB=EPODOC&amp;CC=CN&amp;NR=112862108A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210528&amp;DB=EPODOC&amp;CC=CN&amp;NR=112862108A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG ZHENGSHENG</creatorcontrib><creatorcontrib>LIU YONGSHENG</creatorcontrib><creatorcontrib>ZHOU ZHENG</creatorcontrib><creatorcontrib>ZHU HENGMAN</creatorcontrib><title>Modular reinforcement learning model processing method, system and equipment and storage medium</title><description>The invention relates to a modular reinforcement learning model processing method and device, computer equipment and a storage medium. The method comprises that: interaction data generated by a virtual object in an interaction process with an interaction environment is obtained; the virtual object is controlled by a running component in a reinforcement learning system deployed in the cloud; the reinforcement learning system further comprises a learning assembly and an evaluation assembly; the reinforcement learning model is iteratively trained based on the interaction data through a learning component; in the iterative training process, the reinforcement learning model obtained through iterative training is evaluated through an evaluation component, and whether the reinforcement learning model obtained through iterative training meets interaction conditions or not is judged according to a result obtained through evaluation; and if not, the model associated with the running component is updated according to th</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi7EKwjAURbs4iPoPz13BVJCuUhQXndxLaG5rIMmLecng36vFD3C6nMO586q7silOJ0qwYeDUwyNkctAp2DCSZwNHMXEPkUkgP9hsSF6S4UkHQ3gWG6fblyRz0iM-obHFL6vZoJ1g9dtFtT6f7u1li8gdJOoeAblrb0rVzaFWu-a4_6d5A-AAPYk</recordid><startdate>20210528</startdate><enddate>20210528</enddate><creator>ZHANG ZHENGSHENG</creator><creator>LIU YONGSHENG</creator><creator>ZHOU ZHENG</creator><creator>ZHU HENGMAN</creator><scope>EVB</scope></search><sort><creationdate>20210528</creationdate><title>Modular reinforcement learning model processing method, system and equipment and storage medium</title><author>ZHANG ZHENGSHENG ; LIU YONGSHENG ; ZHOU ZHENG ; ZHU HENGMAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN112862108A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</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 ZHENGSHENG</creatorcontrib><creatorcontrib>LIU YONGSHENG</creatorcontrib><creatorcontrib>ZHOU ZHENG</creatorcontrib><creatorcontrib>ZHU HENGMAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG ZHENGSHENG</au><au>LIU YONGSHENG</au><au>ZHOU ZHENG</au><au>ZHU HENGMAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Modular reinforcement learning model processing method, system and equipment and storage medium</title><date>2021-05-28</date><risdate>2021</risdate><abstract>The invention relates to a modular reinforcement learning model processing method and device, computer equipment and a storage medium. The method comprises that: interaction data generated by a virtual object in an interaction process with an interaction environment is obtained; the virtual object is controlled by a running component in a reinforcement learning system deployed in the cloud; the reinforcement learning system further comprises a learning assembly and an evaluation assembly; the reinforcement learning model is iteratively trained based on the interaction data through a learning component; in the iterative training process, the reinforcement learning model obtained through iterative training is evaluated through an evaluation component, and whether the reinforcement learning model obtained through iterative training meets interaction conditions or not is judged according to a result obtained through evaluation; and if not, the model associated with the running component is updated according to th</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN112862108A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Modular reinforcement learning model processing method, system and equipment and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T19%3A15%3A36IST&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%20ZHENGSHENG&rft.date=2021-05-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN112862108A%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