Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities

We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\tilde{\mathcal{O}}(\sqrt{DSAT})$ up...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org 2019-12
Hauptverfasser:	Tossou, Aristide, Basu, Debabrota, Dimitrakakis, Christos
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Communication Confidence intervals Decision theory Lower bounds Machine learning Markov analysis Markov chains
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title	arXiv.org
container_volume
creator	Tossou, Aristide Basu, Debabrota Dimitrakakis, Christos
description	We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\tilde{\mathcal{O}}(\sqrt{DSAT})$ up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms.
format	Article
fullrecord	<record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2232264998</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2232264998</sourcerecordid><originalsourceid>FETCH-proquest_journals_22322649983</originalsourceid><addsrcrecordid>eNqNi80KgkAURocgSMp3GGgt2B013RZGQRRErWWQa1zRGZ2f92-CHqDNdxbfOQsWgRC7pMwAViy2tk_TFIo95LmI2OuG0iR6cjTKgd-_JOuo5Q8k1WnT4ojK8WuwFKk39_a79TiRoTYUBzTKuuDyi8LZy4Ecod2wZScHi_GPa7Y91c_jOZmMnj1a1_TaGxWuBkAAFFlVleI_6wMyhUG6</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2232264998</pqid></control><display><type>article</type><title>Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities</title><source>Free E- Journals</source><creator>Tossou, Aristide ; Basu, Debabrota ; Dimitrakakis, Christos</creator><creatorcontrib>Tossou, Aristide ; Basu, Debabrota ; Dimitrakakis, Christos</creatorcontrib><description>We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\tilde{\mathcal{O}}(\sqrt{DSAT})$ up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Communication ; Confidence intervals ; Decision theory ; Lower bounds ; Machine learning ; Markov analysis ; Markov chains</subject><ispartof>arXiv.org, 2019-12</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Tossou, Aristide</creatorcontrib><creatorcontrib>Basu, Debabrota</creatorcontrib><creatorcontrib>Dimitrakakis, Christos</creatorcontrib><title>Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities</title><title>arXiv.org</title><description>We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\tilde{\mathcal{O}}(\sqrt{DSAT})$ up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms.</description><subject>Algorithms</subject><subject>Communication</subject><subject>Confidence intervals</subject><subject>Decision theory</subject><subject>Lower bounds</subject><subject>Machine learning</subject><subject>Markov analysis</subject><subject>Markov chains</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi80KgkAURocgSMp3GGgt2B013RZGQRRErWWQa1zRGZ2f92-CHqDNdxbfOQsWgRC7pMwAViy2tk_TFIo95LmI2OuG0iR6cjTKgd-_JOuo5Q8k1WnT4ojK8WuwFKk39_a79TiRoTYUBzTKuuDyi8LZy4Ecod2wZScHi_GPa7Y91c_jOZmMnj1a1_TaGxWuBkAAFFlVleI_6wMyhUG6</recordid><startdate>20191211</startdate><enddate>20191211</enddate><creator>Tossou, Aristide</creator><creator>Basu, Debabrota</creator><creator>Dimitrakakis, Christos</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20191211</creationdate><title>Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities</title><author>Tossou, Aristide ; Basu, Debabrota ; Dimitrakakis, Christos</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_22322649983</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Communication</topic><topic>Confidence intervals</topic><topic>Decision theory</topic><topic>Lower bounds</topic><topic>Machine learning</topic><topic>Markov analysis</topic><topic>Markov chains</topic><toplevel>online_resources</toplevel><creatorcontrib>Tossou, Aristide</creatorcontrib><creatorcontrib>Basu, Debabrota</creatorcontrib><creatorcontrib>Dimitrakakis, Christos</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tossou, Aristide</au><au>Basu, Debabrota</au><au>Dimitrakakis, Christos</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities</atitle><jtitle>arXiv.org</jtitle><date>2019-12-11</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\tilde{\mathcal{O}}(\sqrt{DSAT})$ up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext	fulltext
identifier	EISSN: 2331-8422
ispartof	arXiv.org, 2019-12
issn	2331-8422
language	eng
recordid	cdi_proquest_journals_2232264998
source	Free E- Journals
subjects	Algorithms Communication Confidence intervals Decision theory Lower bounds Machine learning Markov analysis Markov chains
title	Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
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%3A42%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Near-optimal%20Optimistic%20Reinforcement%20Learning%20using%20Empirical%20Bernstein%20Inequalities&rft.jtitle=arXiv.org&rft.au=Tossou,%20Aristide&rft.date=2019-12-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2232264998%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2232264998&rft_id=info:pmid/&rfr_iscdi=true