MODEL-BASED REINFORCEMENT LEARNING

A computer that includes a processor and a memory, the memory including instructions executable by the processor to train an agent neural network to input a first state and output a first action, input the first action to an environment and determine a second state and a reward. Koopman model neural...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chakraborty, Neeloy, Balakrishnan, Kaushik, Upadhyay, Devesh
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
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	Chakraborty, Neeloy Balakrishnan, Kaushik Upadhyay, Devesh
description	A computer that includes a processor and a memory, the memory including instructions executable by the processor to train an agent neural network to input a first state and output a first action, input the first action to an environment and determine a second state and a reward. Koopman model neural network can be trained based on the first state, the first action and the second state to determine a fake state. The agent neural network can be re-trained and the Koopman model neural network can be re-trained based on reinforcement learning including the first state, the first action, the second state, the fake state, and the reward.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024320505A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024320505A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024320505A13</originalsourceid><addsrcrecordid>eNrjZFDy9Xdx9dF1cgx2dVEIcvX0c_MPcnb1dfULUfBxdQzy8_Rz52FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJsZGBqYGpo6GxsSpAgC8QCNJ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MODEL-BASED REINFORCEMENT LEARNING</title><source>esp@cenet</source><creator>Chakraborty, Neeloy ; Balakrishnan, Kaushik ; Upadhyay, Devesh</creator><creatorcontrib>Chakraborty, Neeloy ; Balakrishnan, Kaushik ; Upadhyay, Devesh</creatorcontrib><description>A computer that includes a processor and a memory, the memory including instructions executable by the processor to train an agent neural network to input a first state and output a first action, input the first action to an environment and determine a second state and a reward. Koopman model neural network can be trained based on the first state, the first action and the second state to determine a fake state. The agent neural network can be re-trained and the Koopman model neural network can be re-trained based on reinforcement learning including the first state, the first action, the second state, the fake state, and the reward.</description><language>eng</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=20240926&DB=EPODOC&CC=US&NR=2024320505A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240926&DB=EPODOC&CC=US&NR=2024320505A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Chakraborty, Neeloy</creatorcontrib><creatorcontrib>Balakrishnan, Kaushik</creatorcontrib><creatorcontrib>Upadhyay, Devesh</creatorcontrib><title>MODEL-BASED REINFORCEMENT LEARNING</title><description>A computer that includes a processor and a memory, the memory including instructions executable by the processor to train an agent neural network to input a first state and output a first action, input the first action to an environment and determine a second state and a reward. Koopman model neural network can be trained based on the first state, the first action and the second state to determine a fake state. The agent neural network can be re-trained and the Koopman model neural network can be re-trained based on reinforcement learning including the first state, the first action, the second state, the fake state, and the reward.</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>eNrjZFDy9Xdx9dF1cgx2dVEIcvX0c_MPcnb1dfULUfBxdQzy8_Rz52FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJsZGBqYGpo6GxsSpAgC8QCNJ</recordid><startdate>20240926</startdate><enddate>20240926</enddate><creator>Chakraborty, Neeloy</creator><creator>Balakrishnan, Kaushik</creator><creator>Upadhyay, Devesh</creator><scope>EVB</scope></search><sort><creationdate>20240926</creationdate><title>MODEL-BASED REINFORCEMENT LEARNING</title><author>Chakraborty, Neeloy ; Balakrishnan, Kaushik ; Upadhyay, Devesh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024320505A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</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>Chakraborty, Neeloy</creatorcontrib><creatorcontrib>Balakrishnan, Kaushik</creatorcontrib><creatorcontrib>Upadhyay, Devesh</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chakraborty, Neeloy</au><au>Balakrishnan, Kaushik</au><au>Upadhyay, Devesh</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MODEL-BASED REINFORCEMENT LEARNING</title><date>2024-09-26</date><risdate>2024</risdate><abstract>A computer that includes a processor and a memory, the memory including instructions executable by the processor to train an agent neural network to input a first state and output a first action, input the first action to an environment and determine a second state and a reward. Koopman model neural network can be trained based on the first state, the first action and the second state to determine a fake state. The agent neural network can be re-trained and the Koopman model neural network can be re-trained based on reinforcement learning including the first state, the first action, the second state, the fake state, and the reward.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2024320505A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	MODEL-BASED REINFORCEMENT LEARNING
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T11%3A51%3A41IST&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=Chakraborty,%20Neeloy&rft.date=2024-09-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024320505A1%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