{"entities":{"Q6077159":{"pageid":13211467,"ns":120,"title":"Item:Q6077159","lastrevid":93873191,"modified":"2026-06-05T05:19:57Z","type":"item","id":"Q6077159","labels":{"en":{"language":"en","value":"Q-Learning With Uniformly Bounded Variance"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7741777"}},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6077159$985D1025-FD6D-4894-ADB8-9CA5E150F2DD","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"9191f3d326df6c6ad9bc6a0dbfe01b61fe3f73e0","datavalue":{"value":{"text":"Q-Learning With Uniformly Bounded Variance","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6077159$E78C56AB-FABA-408F-B54D-198F2C995118","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"7e67a617bf97d55f17f714d9c87b2687cef21f97","datavalue":{"value":{"entity-type":"item","numeric-id":2070008,"id":"Q2070008"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6077159$B9179E38-0D9E-4932-8600-7024550150CD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"9e25af83a6fca160fe385237404758ddde5c625e","datavalue":{"value":{"entity-type":"item","numeric-id":313149,"id":"Q313149"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6077159$0FCCB5EE-31CA-436A-BBEF-9BCCC1EAF60B","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"231075b9dab1b13e4c64992ef81666085035687e","datavalue":{"value":{"entity-type":"item","numeric-id":123639,"id":"Q123639"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6077159$8E3455C9-D73E-499C-BDFA-45716D0EACD9","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"75720be84732b5e4c6160ae45afc596463d1f635","datavalue":{"value":{"time":"+2023-09-25T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6077159$DA687C73-68C4-4731-B9AB-B9AE53A87705","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"0d5eef6e848157326ce3189563feefa6213bff81","datavalue":{"value":"93-XX","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6077159$5694FC61-4AF1-486E-912F-817A58060349","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"03dc19523360717df68baae6468f916ceeea571a","datavalue":{"value":"7741777","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6077159$DCBB87C0-3AE6-4CFF-9B77-1E0EEBC1A59B","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"9c5166404b8821726545f8a3a9ab53c350e2fe2b","datavalue":{"value":"Q-learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q6077159$3B59D000-4DE1-434F-8554-35DA7BF9A870","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"0eba36491ceba92f4fa588ab86e9f4db209038e4","datavalue":{"value":"reinforcement learning (RL)","type":"string"},"datatype":"string"},"type":"statement","id":"Q6077159$90609C59-2647-4921-85A8-B2D3D80AB36D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"6d35e880ae23fd41bbf85e0798dfd54bb17d4ffe","datavalue":{"value":"stochastic optimal control","type":"string"},"datatype":"string"},"type":"statement","id":"Q6077159$E836B1C3-BC64-49DB-84FE-9018B1B3BFE2","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6077159$7B00216E-3A8F-4236-83BD-1C0744DB0B6A","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"4be7adb19d9804497fc5fe4e55480e55b647b015","datavalue":{"value":"https://doi.org/10.1109/tac.2021.3133184","type":"string"},"datatype":"url"},"type":"statement","id":"Q6077159$FA451B2D-66EB-44F4-B06A-6FA721E16DE6","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"2cde90d70c9fa4aa93a2c2ae018c7eaae89034d8","datavalue":{"value":"W4205185654","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6077159$5DE42D1C-C4C6-4BE1-A863-F131B201817A","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"34379c8f1d1acdd8b41595bfc5a17a9cb9c639bc","datavalue":{"value":"10.1109/TAC.2021.3133184","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6077159$833894E4-8770-4E67-B5A2-4392F08BB190","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Q-Learning With Uniformly Bounded Variance","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Q-Learning_With_Uniformly_Bounded_Variance"}}}}}