{"entities":{"Q6345675":{"pageid":13480460,"ns":120,"title":"Item:Q6345675","lastrevid":102934478,"modified":"2026-06-06T05:56:13Z","type":"item","id":"Q6345675","labels":{"en":{"language":"en","value":"Batch Policy Learning in Average Reward Markov Decision Processes"}},"descriptions":{"en":{"language":"en","value":"scientific article"}},"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":"Q6345675$8331F341-D1F4-461E-AEE9-7317C64625A0","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"613932c2e2b39a35d6a6525605b39cb7817af50a","datavalue":{"value":{"time":"+2020-07-22T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6345675$791DC68A-A4AC-47EC-A5DE-0D60E5AD8BB7","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"514c4be8e67a63dd5b6713bb819758bc2d9aab6d","datavalue":{"value":"2007.11771","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$96A41495-5B63-42CA-B750-C4B8C34B1FC6","rank":"normal"}],"P22":[{"mainsnak":{"snaktype":"value","property":"P22","hash":"2425efcc9b3f19f1145afc4b21ab66cac71c91ae","datavalue":{"value":"math.ST","type":"string"},"datatype":"string"},"type":"statement","id":"Q6345675$90EE43DC-A4BA-4639-B29B-618B6CB8E9F8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P22","hash":"2f2e57240622252e683460d1060f02c9996da311","datavalue":{"value":"stat.ML","type":"string"},"datatype":"string"},"type":"statement","id":"Q6345675$8744E0DD-7ED8-4FC1-9E25-6885B8FA037E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P22","hash":"d35dc51b4a62fd6d7600c5d09b56c886534bd872","datavalue":{"value":"stat.TH","type":"string"},"datatype":"string"},"type":"statement","id":"Q6345675$6348EB67-BBF2-4D29-9E49-54086932C822","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"7284bffc5ff146d4d33189dffedf5e3837449046","datavalue":{"value":{"entity-type":"item","numeric-id":2071412,"id":"Q2071412"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$63CE33BD-F760-4927-9370-2381EEB3523D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"2c6f2c2231317ff985ab1e3b82e55b77cc2d5f54","datavalue":{"value":{"entity-type":"item","numeric-id":1616326,"id":"Q1616326"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$232360B7-C46D-49D1-A72B-235C282FE1C3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"5d12e9605457dc5e36b5e554e7653c90cf36eccf","datavalue":{"value":{"entity-type":"item","numeric-id":2112816,"id":"Q2112816"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$B9822906-C8D2-433B-ACF1-E98938BD109A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"27f8a19a18cc0c008fed5c947fb6b808082aeae8","datavalue":{"value":{"entity-type":"item","numeric-id":2071413,"id":"Q2071413"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$C35B5C4C-7450-4BA1-B5F6-8EF35B6C0F75","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"49f0b6963bb0a1767a05e08b955c13e37b841ef4","datavalue":{"value":{"entity-type":"item","numeric-id":548553,"id":"Q548553"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$268ABBD4-3EEF-448D-8F2B-7BE46F150632","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$1E19EA5C-E4A1-4C85-8AC6-34883023989A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"3866ee96b4b7ddfafdb7b788eaa87fdd43bbf474","datavalue":{"value":"62G05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$AD28E231-EAFF-4B97-8284-7A558A5087B6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"48a59f52dcfcc38cd6697e0ef07319031311895b","datavalue":{"value":"62H30","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$E8157B5E-8834-4A76-A650-56B041757442","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$B0F008E0-7B0F-41C7-83DE-6C5A572477D6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"708a6f1a75f978962215fcdf6748c16c77f4fd6e","datavalue":{"value":"62P10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$7D0B6D03-7BC2-4A12-880B-E6FD807D2FA1","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"ef79f339f7f12c9b3cc612b7f78bffc6613e5c9e","datavalue":{"value":"10.1214/22-AOS2231","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6345675$93D96B4C-A123-493A-B72B-189956D7CC01","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$BD1D4195-7523-44E4-AEA5-4D17B4F5A846","rank":"normal"}],"P1676":[{"mainsnak":{"snaktype":"value","property":"P1676","hash":"4f3c13523e866daab70dd26537db53c95c32e7fc","datavalue":{"value":{"entity-type":"item","numeric-id":2112817,"id":"Q2112817"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6345675$84BBE0E2-1C11-4EA4-BBE4-60593B01D2FF","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Batch Policy Learning in Average Reward Markov Decision Processes","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Batch_Policy_Learning_in_Average_Reward_Markov_Decision_Processes"}}}}}