{"entities":{"Q6600840":{"pageid":14211997,"ns":120,"title":"Item:Q6600840","lastrevid":96042455,"modified":"2026-06-05T10:17:38Z","type":"item","id":"Q6600840","labels":{"en":{"language":"en","value":"Statistical inference of the value function for reinforcement learning in infinite-horizon settings"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7909595"}},"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":"Q6600840$16C31E07-BB01-4931-8F88-9FB1C791FE7D","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"78b727ecfcdd189a5247f1cff93a98b4bdf6979f","datavalue":{"value":{"text":"Statistical inference of the value function for reinforcement learning in infinite-horizon settings","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6600840$F28C3E03-F443-4FCE-A6B2-487396F0FF6B","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"b4b44e370773e3edb849b98272f98711c75a7d54","datavalue":{"value":{"entity-type":"item","numeric-id":330446,"id":"Q330446"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6600840$20C30BD9-1BA0-456A-B34C-14375FF8FCD1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"ed3d1d5556642329b4705024951c29bed03b6dd8","datavalue":{"value":{"entity-type":"item","numeric-id":281232,"id":"Q281232"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6600840$A0154217-6696-4979-8E46-DA9B7AC909E6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"12b6b05b14d3ae998be4d76e7d26608788cb0b1f","datavalue":{"value":{"entity-type":"item","numeric-id":1676160,"id":"Q1676160"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6600840$C7D27DDE-3064-4156-A950-3755DD69D500","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"c99f006ac503f8cd8f882e747c3a0e669738d625","datavalue":{"value":{"entity-type":"item","numeric-id":247573,"id":"Q247573"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6600840$CE949E17-D884-4E5C-B6FB-5E13A9B8F02B","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"72dcb8981640ed1ad40a5e60920800b850b2d8cc","datavalue":{"value":{"entity-type":"item","numeric-id":6569467,"id":"Q6569467"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6600840$58B9F21D-5EC2-4D84-B63F-0ABF994FDEC9","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"2c5f03d38e864f343b57fd7b32b628d264834b70","datavalue":{"value":{"time":"+2024-09-10T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6600840$45B3301A-F6C3-458C-B001-66191886E585","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"923277c2ca15164b9d1e9edd451ca037b356ac9e","datavalue":{"value":"62-XX","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6600840$8C828E83-D281-4164-8A66-8B5D56A61176","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"e5939c4a9fd1dac93e3447bb4e41a94f1023ba19","datavalue":{"value":"7909595","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6600840$01B00EA9-83EA-496E-BA47-8B2E82FB48E6","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"9c06994aa4d100489b87ca89f1593804103b77f5","datavalue":{"value":"bidirectional asymptotics","type":"string"},"datatype":"string"},"type":"statement","id":"Q6600840$AFCFB0BC-3471-46BB-8D30-4404B2335F66","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"cf884aa5efe2e0d5f6ec433d7d6261a73750c484","datavalue":{"value":"confidence interval","type":"string"},"datatype":"string"},"type":"statement","id":"Q6600840$4B0354C8-FBDD-41BA-A8E2-A78DF9F6FC76","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"826a3a8351e0b04d5438627011bf3bf07dab622b","datavalue":{"value":"infinite horizons","type":"string"},"datatype":"string"},"type":"statement","id":"Q6600840$4C621B85-5A8F-43FB-B218-685A92A212E2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q6600840$C37B6673-26FE-4C2F-8D47-018857B2EF3D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"60a9ddaad371c5de99845b002d7261e34b63d90c","datavalue":{"value":"value function","type":"string"},"datatype":"string"},"type":"statement","id":"Q6600840$07780DD6-37F0-464B-ABBB-8AE956AA7B3C","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":"Q6600840$1898635B-4EC5-41AC-A9E9-40801404FA07","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"9224ed4db9371b8b81a31273457363c4dc711652","datavalue":{"value":"10.1111/RSSB.12465","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6600840$0733A770-B37C-4406-B267-7C92D0AE3474","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Statistical inference of the value function for reinforcement learning in infinite-horizon settings","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Statistical_inference_of_the_value_function_for_reinforcement_learning_in_infinite-horizon_settings"}}}}}