{"entities":{"Q7327803":{"pageid":31378861,"ns":120,"title":"Item:Q7327803","lastrevid":107826176,"modified":"2026-10-27T12:41:15Z","type":"item","id":"Q7327803","labels":{"en":{"language":"en","value":"PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time 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":"Q7327803$6BEE6D3A-F921-4863-89D0-BB7E6D7601EA","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":"Q7327803$94F9E753-CC60-44BA-9CBC-840ABBB76DCC","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"324a7a454c3166099375e9fd0c607e32750c4046","datavalue":{"value":"2606.21925","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7327803$FF9447B4-F10D-496F-A23D-55D1869E95D8","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"15a4bfcf0bd6c32e705f362a338fbafc81665a33","datavalue":{"value":{"entity-type":"item","numeric-id":828490,"id":"Q828490"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7327803$2334483A-C55C-4436-B8E9-9189A6CB4910","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"f168fdf687ee4f2e4ac71df262cc90d02e7c2a33","datavalue":{"value":{"entity-type":"item","numeric-id":7327802,"id":"Q7327802"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7327803$F40090B1-7256-445D-8BBB-B432940D18D3","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":"Q7327803$ED073EC2-E355-4C4C-AC2E-1D0780BA556E","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7327803$AEC6A654-2A21-4A37-AC78-85794CA0779B","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time Control","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/PhiBE-Q-Learning:_Bridging_Off-Policy_Reinforcement_Learning_and_Continuous-Time_Control"}}}}}