{"entities":{"Q7125798":{"pageid":21992040,"ns":120,"title":"Item:Q7125798","lastrevid":106894787,"modified":"2026-10-23T08:51:28Z","type":"item","id":"Q7125798","labels":{"en":{"language":"en","value":"Reinforcement Learning in Decentralized Stochastic Control Systems with Partial History Sharing"}},"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":"Q7125798$A3EE5634-9A6A-4026-A4FA-CE393D594111","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"15b8c83b98b5e742706b93d4f05f24acb70b28a2","datavalue":{"value":{"time":"+2020-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7125798$9D06CFA2-7875-4ECE-B4EA-40000839B7DF","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"0d14455a62a98b6af606c6ffbb9732147f14f448","datavalue":{"value":"2012.02051","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7125798$C7215260-3D44-4D22-8262-70E1412B32FD","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"ad0bbf21ae9d0cdaf3f60176c37e791e4c63b034","datavalue":{"value":{"entity-type":"item","numeric-id":5853832,"id":"Q5853832"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7125798$3C6C5228-056F-4AEF-839A-C591E2C08B64","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"da99c62fa5fee543eecc5f7518f1762307417410","datavalue":{"value":{"entity-type":"item","numeric-id":333076,"id":"Q333076"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7125798$4AC2C5F8-A726-4513-AF32-E81307C23712","rank":"normal"}],"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7125798$C8B72203-94DA-49B3-9D36-838D7310CF44","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":"Q7125798$23635A02-E655-4BD5-BE5A-998F86B7F70B","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Reinforcement Learning in Decentralized Stochastic Control Systems with Partial History Sharing","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Reinforcement_Learning_in_Decentralized_Stochastic_Control_Systems_with_Partial_History_Sharing"}}}}}