{"entities":{"Q6506966":{"pageid":14085924,"ns":120,"title":"Item:Q6506966","lastrevid":95369564,"modified":"2026-06-05T08:56:08Z","type":"item","id":"Q6506966","labels":{"en":{"language":"en","value":"Connecting Stochastic Optimal Control and Reinforcement Learning"}},"descriptions":{"en":{"language":"en","value":"scientific article from arXiv"}},"aliases":{},"claims":{"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":"Q6506966$1634B30C-A22B-4B3B-95A6-EE3F4BD01E4E","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"9e07235fa17d2f12dfb0eefb084b9ce71217165b","datavalue":{"value":{"text":"Connecting Stochastic Optimal Control and Reinforcement Learning","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6506966$CE6F083A-FC84-47BA-98B6-E84FED112797","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"dbdb8b8069f4d8802dd130f196097330d70a9892","datavalue":{"value":{"entity-type":"item","numeric-id":6402006,"id":"Q6402006"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6506966$D5F5CB48-2113-4E0D-AD30-14CF5A763318","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"ec5c81a9feadb301888b303807d8a375a0a34946","datavalue":{"value":{"entity-type":"item","numeric-id":2022694,"id":"Q2022694"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6506966$C224D930-2296-4044-A97C-1E318C38D61F","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"459a0afd1db870cf11b54d7d1fcd11f9927d05a2","datavalue":{"value":"49-XX","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6506966$DC888DC3-7143-4692-A0D9-06BA1F3387DE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"0d5eef6e848157326ce3189563feefa6213bff81","datavalue":{"value":"93-XX","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6506966$651782A9-05CA-4760-84EE-9892472BA895","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"62a49b155c9af634e6c3562b1547da1f7c08791a","datavalue":{"value":"68-XX","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6506966$5B8A036F-C6C7-4F87-AF5E-4BEFCBE15188","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":"Q6506966$75E7A4D9-7A56-4EDC-A98C-96D586DE1359","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"f6688b3c56ef83f521f5a23ccd32b5d9f141ac27","datavalue":{"value":"2211.02474","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6506966$B4B1F86B-9918-4D3D-B83D-8F87FACE6076","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Connecting Stochastic Optimal Control and Reinforcement Learning","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Connecting_Stochastic_Optimal_Control_and_Reinforcement_Learning"}}}}}