The actor-critic algorithm as multi-time-scale stochastic approximation

The actor-critic algorithm of Barto and others for simulation-based optimization of Markov decision processes is cast as a two time scale stochastic approximation. Convergence analysis, approximation issues and an example are studied.

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Sadhana (Bangalore) 1997-08, Vol.22 (4), p.525-543
Hauptverfasser:	Borkar, Vivek S, Konda, Vijaymohan R
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Approximation Markov processes Mathematical analysis Optimization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	543
container_issue	4
container_start_page	525
container_title	Sadhana (Bangalore)
container_volume	22
creator	Borkar, Vivek S Konda, Vijaymohan R
description	The actor-critic algorithm of Barto and others for simulation-based optimization of Markov decision processes is cast as a two time scale stochastic approximation. Convergence analysis, approximation issues and an example are studied.
doi_str_mv	10.1007/BF02745577
format	Article
fullrecord	<record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2786543821</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2786543821</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-7743930d1934282a9019cb222538c98c1095f6d9b50fa226524bdc2ba68a9aff3</originalsourceid><addsrcrecordid>eNpFkE1LxDAYhIMouK5e_AUFb0I0efN91MVdhQUv67mkaWu7tJuapKD_3ugKnmYODzPDIHRNyR0lRN0_rgkoLoRSJ2hBjGJYSaVOswchMXBjztFFjHuSMaLZAm12XVNYl3zALvSpd4Ud3n123VjYWIzzkHqc-rHB0dmhKWLyrrPxF5ym4D_70abeHy7RWWuH2Fz96RK9rZ92q2e8fd28rB622IFhCSvFmWGkpoZx0GANocZVACCYdkY7SoxoZW0qQVoLIAXwqnZQWamtsW3LlujmmJu7P-YmpnLv53DIlSUoLQVnGmimbo-UCz7G0LTlFPLQ8FVSUv4cVf4fxb4B3ARZwQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2786543821</pqid></control><display><type>article</type><title>The actor-critic algorithm as multi-time-scale stochastic approximation</title><source>Indian Academy of Sciences</source><source>EZB-FREE-00999 freely available EZB journals</source><source>SpringerLink Journals - AutoHoldings</source><creator>Borkar, Vivek S ; Konda, Vijaymohan R</creator><creatorcontrib>Borkar, Vivek S ; Konda, Vijaymohan R</creatorcontrib><description>The actor-critic algorithm of Barto and others for simulation-based optimization of Markov decision processes is cast as a two time scale stochastic approximation. Convergence analysis, approximation issues and an example are studied.</description><identifier>ISSN: 0256-2499</identifier><identifier>EISSN: 0973-7677</identifier><identifier>DOI: 10.1007/BF02745577</identifier><language>eng</language><publisher>Dordrecht: Springer Nature B.V</publisher><subject>Algorithms ; Approximation ; Markov processes ; Mathematical analysis ; Optimization</subject><ispartof>Sadhana (Bangalore), 1997-08, Vol.22 (4), p.525-543</ispartof><rights>Indian Academy of Sciences 1997.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-7743930d1934282a9019cb222538c98c1095f6d9b50fa226524bdc2ba68a9aff3</citedby><cites>FETCH-LOGICAL-c293t-7743930d1934282a9019cb222538c98c1095f6d9b50fa226524bdc2ba68a9aff3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids></links><search><creatorcontrib>Borkar, Vivek S</creatorcontrib><creatorcontrib>Konda, Vijaymohan R</creatorcontrib><title>The actor-critic algorithm as multi-time-scale stochastic approximation</title><title>Sadhana (Bangalore)</title><description>The actor-critic algorithm of Barto and others for simulation-based optimization of Markov decision processes is cast as a two time scale stochastic approximation. Convergence analysis, approximation issues and an example are studied.</description><subject>Algorithms</subject><subject>Approximation</subject><subject>Markov processes</subject><subject>Mathematical analysis</subject><subject>Optimization</subject><issn>0256-2499</issn><issn>0973-7677</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1997</creationdate><recordtype>article</recordtype><recordid>eNpFkE1LxDAYhIMouK5e_AUFb0I0efN91MVdhQUv67mkaWu7tJuapKD_3ugKnmYODzPDIHRNyR0lRN0_rgkoLoRSJ2hBjGJYSaVOswchMXBjztFFjHuSMaLZAm12XVNYl3zALvSpd4Ud3n123VjYWIzzkHqc-rHB0dmhKWLyrrPxF5ym4D_70abeHy7RWWuH2Fz96RK9rZ92q2e8fd28rB622IFhCSvFmWGkpoZx0GANocZVACCYdkY7SoxoZW0qQVoLIAXwqnZQWamtsW3LlujmmJu7P-YmpnLv53DIlSUoLQVnGmimbo-UCz7G0LTlFPLQ8FVSUv4cVf4fxb4B3ARZwQ</recordid><startdate>19970801</startdate><enddate>19970801</enddate><creator>Borkar, Vivek S</creator><creator>Konda, Vijaymohan R</creator><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>19970801</creationdate><title>The actor-critic algorithm as multi-time-scale stochastic approximation</title><author>Borkar, Vivek S ; Konda, Vijaymohan R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-7743930d1934282a9019cb222538c98c1095f6d9b50fa226524bdc2ba68a9aff3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Algorithms</topic><topic>Approximation</topic><topic>Markov processes</topic><topic>Mathematical analysis</topic><topic>Optimization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Borkar, Vivek S</creatorcontrib><creatorcontrib>Konda, Vijaymohan R</creatorcontrib><collection>CrossRef</collection><jtitle>Sadhana (Bangalore)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Borkar, Vivek S</au><au>Konda, Vijaymohan R</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The actor-critic algorithm as multi-time-scale stochastic approximation</atitle><jtitle>Sadhana (Bangalore)</jtitle><date>1997-08-01</date><risdate>1997</risdate><volume>22</volume><issue>4</issue><spage>525</spage><epage>543</epage><pages>525-543</pages><issn>0256-2499</issn><eissn>0973-7677</eissn><abstract>The actor-critic algorithm of Barto and others for simulation-based optimization of Markov decision processes is cast as a two time scale stochastic approximation. Convergence analysis, approximation issues and an example are studied.</abstract><cop>Dordrecht</cop><pub>Springer Nature B.V</pub><doi>10.1007/BF02745577</doi><tpages>19</tpages><oa>free_for_read</oa></addata></record>
fulltext	fulltext
identifier	ISSN: 0256-2499
ispartof	Sadhana (Bangalore), 1997-08, Vol.22 (4), p.525-543
issn	0256-2499 0973-7677
language	eng
recordid	cdi_proquest_journals_2786543821
source	Indian Academy of Sciences; EZB-FREE-00999 freely available EZB journals; SpringerLink Journals - AutoHoldings
subjects	Algorithms Approximation Markov processes Mathematical analysis Optimization
title	The actor-critic algorithm as multi-time-scale stochastic approximation
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T10%3A05%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20actor-critic%20algorithm%20as%20multi-time-scale%20stochastic%20approximation&rft.jtitle=Sadhana%20(Bangalore)&rft.au=Borkar,%20Vivek%20S&rft.date=1997-08-01&rft.volume=22&rft.issue=4&rft.spage=525&rft.epage=543&rft.pages=525-543&rft.issn=0256-2499&rft.eissn=0973-7677&rft_id=info:doi/10.1007/BF02745577&rft_dat=%3Cproquest_cross%3E2786543821%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2786543821&rft_id=info:pmid/&rfr_iscdi=true