{"entities":{"Q7399177":{"pageid":31728884,"ns":120,"title":"Item:Q7399177","lastrevid":108076565,"modified":"2026-10-27T14:50:50Z","type":"item","id":"Q7399177","labels":{"en":{"language":"en","value":"Hamiltonian Primal-Dual Policy Reinforcement Learning for Derivative-Free Model-Based Control"}},"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":"Q7399177$DE3564E5-4DB5-4667-9A96-3285A6906FCA","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"fea8258efc0c807aa3a84f12ebcd68838427a662","datavalue":{"value":{"time":"+2026-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7399177$68C2D1F9-74E8-44C5-A6A0-F54C92158275","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"a95b9b468a21e68965d5eb020d0829cbcbde5b92","datavalue":{"value":"2610.18524","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7399177$976F63AA-ABF7-49E1-8042-4EDBE7BA4885","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"460acbf3664cbb007b97b8081c0dbd02db7b8aca","datavalue":{"value":{"entity-type":"item","numeric-id":1627463,"id":"Q1627463"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7399177$23F3ACC9-638B-409E-AF47-AB233D18585B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"c0529ceb3a392ab716e46abbfb1075b713068f8c","datavalue":{"value":{"entity-type":"item","numeric-id":7399175,"id":"Q7399175"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7399177$32FA1760-655D-42EB-B1EE-3CC7C08B4D7C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"28907a852cce47e76ae4028328976a0753f2f360","datavalue":{"value":{"entity-type":"item","numeric-id":7399176,"id":"Q7399176"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7399177$95A89225-9083-42E7-945C-75DC96CFD6CC","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"a8ad7df5c4877384f3a6c125dfaf3d264fa00b2b","datavalue":{"value":{"entity-type":"item","numeric-id":335254,"id":"Q335254"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7399177$C9F3803A-6A10-48EC-85D5-974AAE84D921","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":"Q7399177$4C2B0266-32E1-4F89-868A-536C867ABFB7","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":"Q7399177$20DA2505-1081-4DBB-AFA3-706EEDDA9C4F","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Hamiltonian Primal-Dual Policy Reinforcement Learning for Derivative-Free Model-Based Control","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Hamiltonian_Primal-Dual_Policy_Reinforcement_Learning_for_Derivative-Free_Model-Based_Control"}}}}}