{"entities":{"Q7198533":{"pageid":22230311,"ns":120,"title":"Item:Q7198533","lastrevid":107512175,"modified":"2026-10-27T10:22:43Z","type":"item","id":"Q7198533","labels":{"en":{"language":"en","value":"Asymptotically optimal reinforcement learning in Block Markov Decision Processes"}},"descriptions":{"en":{"language":"en","value":"scientific article from arXiv"}},"aliases":{},"claims":{"P22":[{"mainsnak":{"snaktype":"value","property":"P22","hash":"5a9a9eaa7fd7e010f3960691b4ec6b49e1992fea","datavalue":{"value":"cs.LG","type":"string"},"datatype":"string"},"type":"statement","id":"Q7198533$C3CFBAE7-B6A9-4A5F-B8B0-5BF993113719","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"1533ef58fe3b6ac0b6e76c86b8ed9a818696c893","datavalue":{"value":{"time":"+2025-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7198533$48DF5820-8969-49EF-B47E-ED3EDC67795D","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"df0da7f2134764ac6bd3f6e4e4bc5e3cd9d0fc20","datavalue":{"value":"2510.13748","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7198533$E8E97541-89FE-4A6E-AFC7-74EF7985D3C5","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"0aec2f9e8106918d69ba16ae3145d89adf99df84","datavalue":{"value":{"entity-type":"item","numeric-id":6083850,"id":"Q6083850"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7198533$774EBA31-2C51-4050-AB4F-B214B00BD21B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"17b8ad74d16272b64dfd25e7f1c59cdb190cdab9","datavalue":{"value":{"entity-type":"item","numeric-id":4639227,"id":"Q4639227"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7198533$AD61B177-3FE9-42D8-B0E4-C764F0F5FC50","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"694be45197ad0a36069bbcf2eab99c104f316677","datavalue":{"value":{"entity-type":"item","numeric-id":6757982,"id":"Q6757982"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7198533$0F2178AD-BC66-47DF-94AC-0834B134ADA4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"08a7407e3b5d7e23e0b3429f26fc8e91aac794c6","datavalue":{"value":{"entity-type":"item","numeric-id":683322,"id":"Q683322"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7198533$054BC6A8-3391-4AFF-8CAC-EDDAC52B542C","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7198533$15C34082-E988-4A19-A4EB-D678D0A75A5D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"48a59f52dcfcc38cd6697e0ef07319031311895b","datavalue":{"value":"62H30","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7198533$31E39207-2526-43C7-B309-447D32B68FE2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"6a9ff1a146ff44dca747e334413377c148d2df3d","datavalue":{"value":"60J20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7198533$041A2BFD-39B0-40A6-BF79-A3ED06D99455","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":"Q7198533$738E14AC-1E93-4EC5-B420-0399C87488F0","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":"Q7198533$99DC58C6-E622-4BCE-A54A-ED0C70C0F6F1","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Asymptotically optimal reinforcement learning in Block Markov Decision Processes","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Asymptotically_optimal_reinforcement_learning_in_Block_Markov_Decision_Processes"}}}}}