{"entities":{"Q7204139":{"pageid":22250252,"ns":120,"title":"Item:Q7204139","lastrevid":107553191,"modified":"2026-10-27T10:40:42Z","type":"item","id":"Q7204139","labels":{"en":{"language":"en","value":"Adaptive Inverse Reinforcement Learning with Online Off-Policy Data Collection"}},"descriptions":{"en":{"language":"en","value":"scientific article from arXiv"}},"aliases":{},"claims":{"P22":[{"mainsnak":{"snaktype":"value","property":"P22","hash":"5a067f3cc35200b51bab0398d603e2eb9779a610","datavalue":{"value":"math.OC","type":"string"},"datatype":"string"},"type":"statement","id":"Q7204139$0C512692-B6FE-41F2-9EA9-DC5BADADC889","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":"Q7204139$9558EA71-700A-4D93-A76B-5BB9446C7DCD","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"c914acce4bf36629b9f432fc648dca79582ede5f","datavalue":{"value":"2511.15171","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7204139$D2BAD8FC-2594-4742-A7F7-63D8CBA4F589","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"d393224e5293306259228557c49bb4d786265991","datavalue":{"value":{"entity-type":"item","numeric-id":2063843,"id":"Q2063843"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7204139$47A79EBB-329A-4BCA-A7D3-936156B4BA3B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"4982b29e3d68b84bd3a8c94623475e3f5dbee779","datavalue":{"value":{"entity-type":"item","numeric-id":6569591,"id":"Q6569591"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7204139$C9135EF2-BDEE-4ECF-92AC-809A931C4515","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"2e88791b6fc9f9f5fb29f2f1a57b7d71e647fcf2","datavalue":{"value":{"entity-type":"item","numeric-id":314541,"id":"Q314541"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7204139$47E35367-B54C-48F1-941E-CD157ECC2225","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"d3acf2a70982867e33c57d1e9e23d06a211f7eec","datavalue":{"value":{"entity-type":"item","numeric-id":162570,"id":"Q162570"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7204139$98B917B1-7DD4-461E-BBBE-23756F2932F1","rank":"normal"}],"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7204139$AABBF151-6247-4CE7-99AF-58AE10699B7D","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":"Q7204139$6FCCD1F1-3884-4F40-82C4-06DA2D31A6FE","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Adaptive Inverse Reinforcement Learning with Online Off-Policy Data Collection","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Adaptive_Inverse_Reinforcement_Learning_with_Online_Off-Policy_Data_Collection"}}}}}