{"entities":{"Q5405216":{"pageid":7434790,"ns":120,"title":"Item:Q5405216","lastrevid":75718270,"modified":"2026-04-20T18:32:49Z","type":"item","id":"Q5405216","labels":{"en":{"language":"en","value":"Finite-sample analysis of least-squares policy iteration"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 6276207"}},"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":"Q5405216$AF25129E-216C-4449-B141-62BD72A9395E","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"4f4090b692b907123f711d460305743427f972eb","datavalue":{"value":"1433.68361","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5405216$E90E8318-CCB9-47E2-B8C7-0CB7B35F9D0F","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"f5121d197e54c5b8c13ac0fb3cc8014d11320137","datavalue":{"value":{"entity-type":"item","numeric-id":439997,"id":"Q439997"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5405216$AE687C1F-1780-49C7-88F5-D5D4C43C19EE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"9cc1c3ba770c4e5863d80dfbeadef9ce7f6e4c7b","datavalue":{"value":{"entity-type":"item","numeric-id":1049134,"id":"Q1049134"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5405216$4C171BB5-66A5-4522-A9D0-214D6246F358","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"145ddfd84f75b992a56617053b076be347e6cf9b","datavalue":{"value":{"entity-type":"item","numeric-id":366993,"id":"Q366993"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5405216$4CF86165-3EEB-49DF-BDA4-D671FC0BA8D5","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"1832e2b8d11d1c115bb49a23d134e9ef7371fd03","datavalue":{"value":{"time":"+2014-04-01T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q5405216$82E7808B-88CC-459F-BA30-BB488AC013BA","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"c81d79764cba8c99c9033e884979513d4b8dae88","datavalue":{"value":"http://www.jmlr.org/papers/v13/lazaric12a.html","type":"string"},"datatype":"url"},"type":"statement","id":"Q5405216$D98C6935-965C-418F-97F5-E967EE3194E4","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5405216$56C5CA66-E410-4C06-A9D2-E60293B3605E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"5823d607a543702da84952b8d59bfb2f0bb4edc6","datavalue":{"value":"62J05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5405216$BC8654BA-A394-41A0-8087-6AF205976D9D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"6a9ff1a146ff44dca747e334413377c148d2df3d","datavalue":{"value":"60J20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5405216$17BB4A6D-8264-4554-A46B-DB1B98C93C53","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5405216$FB5AEBEE-120F-4B6C-8B21-394C6DFD5215","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"97fe6abe7b1bdb00574d981a8ac5063b6169b93f","datavalue":{"value":"6276207","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5405216$5178F886-3976-4111-A1DA-9714518CB0AB","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fbd1f99995fb6a13da62a377ba6327166316e976","datavalue":{"value":"Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q5405216$73FE14A1-8785-4EC4-9C56-ACED54058F29","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q5405216$46035907-E003-499D-B789-096D80DE87A8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"215a57a10aac585f9ff9124d1e39dbdd39138437","datavalue":{"value":"least-squares temporal-difference","type":"string"},"datatype":"string"},"type":"statement","id":"Q5405216$596E9FF5-9A07-457C-BD7D-3DB9B743D860","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"2d5b38a733b2ed76e27009810188ae948f8c59c9","datavalue":{"value":"least-squares policy iteration","type":"string"},"datatype":"string"},"type":"statement","id":"Q5405216$51D3D962-F125-4936-81AD-09AF7A1ABEBD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"a338c50a31182c4903ee50df62501bf0b5d99a19","datavalue":{"value":"generalization bounds","type":"string"},"datatype":"string"},"type":"statement","id":"Q5405216$3AFA03BF-DA1C-4509-9621-6206985D866C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"990697b7a41613d61d8930d8009493d44d383eaf","datavalue":{"value":"finite-sample analysis","type":"string"},"datatype":"string"},"type":"statement","id":"Q5405216$639742B2-BFAD-4435-82D4-268BABC1E541","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":"Q5405216$24092BFB-E4A9-44E4-AFA0-AA5A2D6019C7","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"81a62751b92f8cd596b8a3c8d08fc874b299d030","datavalue":{"value":{"entity-type":"item","numeric-id":4910565,"id":"Q4910565"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"3f46774f0f1243d422c9ebb39fa3d2348f82e068","datavalue":{"value":{"amount":"+0.8334509134292603","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5405216$B83C4BB8-0D07-4A03-A5BA-45BB6C27926B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"ce60585abc3717428d65857b30bfc95096b6b37c","datavalue":{"value":{"entity-type":"item","numeric-id":5406031,"id":"Q5406031"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0534269105f94346b293e4702aed5afad6ccc816","datavalue":{"value":{"amount":"+0.8317558169364929","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5405216$D6340843-1A97-4B09-8358-4F57BC0DFAA5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"7977b8935a2f9cf112ad48312309630934e1a263","datavalue":{"value":{"entity-type":"item","numeric-id":4826001,"id":"Q4826001"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"600178d4b56818bd7cf95d1ce5356a828d50e4fb","datavalue":{"value":{"amount":"+0.8294392228126526","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5405216$1C11E6F2-D8E8-442B-9449-4C73AD8F30AB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"6d798bfbf8c1004c352d387aaf675f1548d9f74e","datavalue":{"value":{"entity-type":"item","numeric-id":1870310,"id":"Q1870310"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"eeb0d81a59494823bdf750d8fc798ac7a771509d","datavalue":{"value":{"amount":"+0.8056071400642395","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5405216$6538B9A0-EAFB-4C7E-8E70-168794AA8650","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"3c0adbaf55e53717580e9e65225403db2d5172e6","datavalue":{"value":{"entity-type":"item","numeric-id":3096132,"id":"Q3096132"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"91a2248591437fe5caabee0f0806eb8bbf95a999","datavalue":{"value":{"amount":"+0.7817057967185974","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5405216$46EA0106-844C-438D-BEFD-C0A087855981","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Finite-sample analysis of least-squares policy iteration","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Finite-sample_analysis_of_least-squares_policy_iteration"}}}}}