Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games
We study two-player general sum repeated finite games where the rewards of each player are generated from an unknown distribution. Our aim is to find the egalitarian bargaining solution (EBS) for the repeated game, which can lead to much higher rewards than the maximin value of both players. Our mos...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artikel |
| Sprache: | 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 | Tossou, Aristide Dimitrakakis, Christos Rzepecki, Jaroslaw Hofmann, Katja |
| description | We study two-player general sum repeated finite games where the rewards of
each player are generated from an unknown distribution. Our aim is to find the
egalitarian bargaining solution (EBS) for the repeated game, which can lead to
much higher rewards than the maximin value of both players. Our most important
contribution is the derivation of an algorithm that achieves simultaneously,
for both players, a high-probability regret bound of order
$\mathcal{O}(\sqrt[3]{\ln T}\cdot T^{2/3})$ after any $T$ rounds of play. We
demonstrate that our upper bound is nearly optimal by proving a lower bound of
$\Omega(T^{2/3})$ for any algorithm. |
| doi_str_mv | 10.48550/arxiv.1906.01609 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1906_01609</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1906_01609</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-bd5abecaab98fd7055a3486e2ada1a01cd040dccdd1ce33c4c8fc6995b90a8793</originalsourceid><addsrcrecordid>eNotj8FOwzAQRH3hgFo-gBP-gYQ1jh37WFUlILVEgt6jjb2pLDlW5AZU_p5QOM1hRk_zGLsXUFZGKXjEfAlfpbCgSxAa7C07vBHmop3mMGLkbYohEd-dMIYZc8DE49KnkE48JN5QorzMPj5H_k4T4UyeH3DO4cIbHOm8ZjcDxjPd_eeKHZ93x-1LsW-b1-1mX6CubdF7hT05xN6awdegFMrKaHpCjwJBOA8VeOe8F46kdJUzg9PWqt4CmtrKFXv4w159uikv5_N39-vVXb3kD2C7SWA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games</title><source>arXiv.org</source><creator>Tossou, Aristide ; Dimitrakakis, Christos ; Rzepecki, Jaroslaw ; Hofmann, Katja</creator><creatorcontrib>Tossou, Aristide ; Dimitrakakis, Christos ; Rzepecki, Jaroslaw ; Hofmann, Katja</creatorcontrib><description>We study two-player general sum repeated finite games where the rewards of
each player are generated from an unknown distribution. Our aim is to find the
egalitarian bargaining solution (EBS) for the repeated game, which can lead to
much higher rewards than the maximin value of both players. Our most important
contribution is the derivation of an algorithm that achieves simultaneously,
for both players, a high-probability regret bound of order
$\mathcal{O}(\sqrt[3]{\ln T}\cdot T^{2/3})$ after any $T$ rounds of play. We
demonstrate that our upper bound is nearly optimal by proving a lower bound of
$\Omega(T^{2/3})$ for any algorithm.</description><identifier>DOI: 10.48550/arxiv.1906.01609</identifier><language>eng</language><subject>Computer Science - Computer Science and Game Theory ; Computer Science - Learning</subject><creationdate>2019-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1906.01609$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1906.01609$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Tossou, Aristide</creatorcontrib><creatorcontrib>Dimitrakakis, Christos</creatorcontrib><creatorcontrib>Rzepecki, Jaroslaw</creatorcontrib><creatorcontrib>Hofmann, Katja</creatorcontrib><title>Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games</title><description>We study two-player general sum repeated finite games where the rewards of
each player are generated from an unknown distribution. Our aim is to find the
egalitarian bargaining solution (EBS) for the repeated game, which can lead to
much higher rewards than the maximin value of both players. Our most important
contribution is the derivation of an algorithm that achieves simultaneously,
for both players, a high-probability regret bound of order
$\mathcal{O}(\sqrt[3]{\ln T}\cdot T^{2/3})$ after any $T$ rounds of play. We
demonstrate that our upper bound is nearly optimal by proving a lower bound of
$\Omega(T^{2/3})$ for any algorithm.</description><subject>Computer Science - Computer Science and Game Theory</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FOwzAQRH3hgFo-gBP-gYQ1jh37WFUlILVEgt6jjb2pLDlW5AZU_p5QOM1hRk_zGLsXUFZGKXjEfAlfpbCgSxAa7C07vBHmop3mMGLkbYohEd-dMIYZc8DE49KnkE48JN5QorzMPj5H_k4T4UyeH3DO4cIbHOm8ZjcDxjPd_eeKHZ93x-1LsW-b1-1mX6CubdF7hT05xN6awdegFMrKaHpCjwJBOA8VeOe8F46kdJUzg9PWqt4CmtrKFXv4w159uikv5_N39-vVXb3kD2C7SWA</recordid><startdate>20190604</startdate><enddate>20190604</enddate><creator>Tossou, Aristide</creator><creator>Dimitrakakis, Christos</creator><creator>Rzepecki, Jaroslaw</creator><creator>Hofmann, Katja</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190604</creationdate><title>Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games</title><author>Tossou, Aristide ; Dimitrakakis, Christos ; Rzepecki, Jaroslaw ; Hofmann, Katja</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-bd5abecaab98fd7055a3486e2ada1a01cd040dccdd1ce33c4c8fc6995b90a8793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computer Science and Game Theory</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Tossou, Aristide</creatorcontrib><creatorcontrib>Dimitrakakis, Christos</creatorcontrib><creatorcontrib>Rzepecki, Jaroslaw</creatorcontrib><creatorcontrib>Hofmann, Katja</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tossou, Aristide</au><au>Dimitrakakis, Christos</au><au>Rzepecki, Jaroslaw</au><au>Hofmann, Katja</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games</atitle><date>2019-06-04</date><risdate>2019</risdate><abstract>We study two-player general sum repeated finite games where the rewards of
each player are generated from an unknown distribution. Our aim is to find the
egalitarian bargaining solution (EBS) for the repeated game, which can lead to
much higher rewards than the maximin value of both players. Our most important
contribution is the derivation of an algorithm that achieves simultaneously,
for both players, a high-probability regret bound of order
$\mathcal{O}(\sqrt[3]{\ln T}\cdot T^{2/3})$ after any $T$ rounds of play. We
demonstrate that our upper bound is nearly optimal by proving a lower bound of
$\Omega(T^{2/3})$ for any algorithm.</abstract><doi>10.48550/arxiv.1906.01609</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1906.01609 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1906_01609 |
| source | arXiv.org |
| subjects | Computer Science - Computer Science and Game Theory Computer Science - Learning |
| title | Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T15%3A30%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Near-Optimal%20Online%20Egalitarian%20learning%20in%20General%20Sum%20Repeated%20Matrix%20Games&rft.au=Tossou,%20Aristide&rft.date=2019-06-04&rft_id=info:doi/10.48550/arxiv.1906.01609&rft_dat=%3Carxiv_GOX%3E1906_01609%3C/arxiv_GOX%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 |