{"entities":{"Q6737185":{"pageid":14455962,"ns":120,"title":"Item:Q6737185","lastrevid":105887243,"modified":"2026-10-21T12:47:10Z","type":"item","id":"Q6737185","labels":{"en":{"language":"en","value":"On Policy Evaluation Algorithms in Distributional Reinforcement Learning"}},"descriptions":{"en":{"language":"en","value":"scientific article from arXiv"}},"aliases":{},"claims":{"P22":[{"mainsnak":{"snaktype":"value","property":"P22","hash":"2f2e57240622252e683460d1060f02c9996da311","datavalue":{"value":"stat.ML","type":"string"},"datatype":"string"},"type":"statement","id":"Q6737185$D2BF77AC-4900-4963-8FF7-484B02D62802","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"fecb2f2a7c1f813db3a025a7dd8b5d82439618b9","datavalue":{"value":{"time":"+2024-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6737185$A37C0164-1A29-42FF-9ACF-8613AE9CB881","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"cac7b309ad4c60c14a338926d699a0a321f72b1b","datavalue":{"value":"2407.14175","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6737185$1D6F9ABA-8B34-46C7-AF2C-25B5F453DACF","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"e39a248f963c7990965b59e8689df0436fe92913","datavalue":{"value":{"entity-type":"item","numeric-id":784162,"id":"Q784162"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6737185$EA49F60F-AAFF-4D6E-80E2-822400B3FCBB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"c71a6d4e2a59276b58585926cfc8b9368f56a3ea","datavalue":{"value":{"entity-type":"item","numeric-id":370894,"id":"Q370894"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6737185$FA791B03-FF73-4D33-9A89-347E7DC984F9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"091be178568a7368b4814d3a1271e7068fabb0d7","datavalue":{"value":{"entity-type":"item","numeric-id":6153119,"id":"Q6153119"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6737185$594569CC-57A2-4B8C-B084-D3F70F0E2142","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"1aa607685f2faa2d81a018b093e1e66d41eb5a9e","datavalue":{"value":"60E05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6737185$AA5B2055-21DE-4D86-91CD-239F1C6AEF38","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"b030290c7c684268d407edb9b2f13755562a711c","datavalue":{"value":"60H25","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6737185$CA8864D3-EF32-427B-8599-EDB5DC9CA2C7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6737185$4C9C7FA1-8D7D-47A6-8AEF-804F7E688E73","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6737185$3124C5B7-32F8-4EA0-91E8-A8510941430B","rank":"normal"}],"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":"Q6737185$0F718412-C4BD-4162-BE69-C42174D332D6","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6737185$FE688541-A0CA-4803-8F38-0DCFA3CAE88A","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"On Policy Evaluation Algorithms in Distributional Reinforcement Learning","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/On_Policy_Evaluation_Algorithms_in_Distributional_Reinforcement_Learning"}}}}}