{"entities":{"Q6829291":{"pageid":15115684,"ns":120,"title":"Item:Q6829291","lastrevid":56016859,"modified":"2026-02-24T14:11:43Z","type":"item","id":"Q6829291","labels":{"en":{"language":"en","value":"On generalized Bellman equations and temporal-difference learning"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 6982339"}},"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":"Q6829291$D4D53729-0C73-4CAF-B6C2-123B1B7B144F","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"a780d7f839140f574f00238bed5bb9096e7ce3f3","datavalue":{"value":{"text":"On generalized Bellman equations and temporal-difference learning","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6829291$88F225E6-B6A4-47EF-B23A-E413BA99FBB9","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"23e26e4114acd24c5cf3419b8e92a73877676998","datavalue":{"value":"1465.90117","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6829291$569F3811-EA18-4936-8102-8D1FF48C06BC","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"419931659e530ab18949689112de8020c92dca8c","datavalue":{"value":{"entity-type":"item","numeric-id":378729,"id":"Q378729"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6829291$AF701116-7F60-449E-AA86-F426346B63B5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"2ca949b0a8509885c0bdaa48bf07bed6efcbbe8e","datavalue":{"value":{"entity-type":"item","numeric-id":2810883,"id":"Q2810883"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6829291$3A593676-CF6D-44F8-BA54-38F639D5336B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"1d0463f1e7d2643065a0fb126a3a03aa8a0fd3ce","datavalue":{"value":{"entity-type":"item","numeric-id":1049133,"id":"Q1049133"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6829291$7F23B62E-D596-4BE0-8CFE-5A35E3C915D6","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"05810dfd27f2b8a246f7d0a5b34fbcc72e448b7a","datavalue":{"value":{"entity-type":"item","numeric-id":6582882,"id":"Q6582882"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6829291$CA98859C-6895-401A-B5F7-9D9C4EAB29BC","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"864c5420d75ff030f7dfad739513bee1287bf672","datavalue":{"value":{"time":"+2018-11-21T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6829291$A8E96716-494B-4F6E-BA4D-F7DEB1792961","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"1df5b59d1d5d92b5f7def734d3af49cd3dad0cc1","datavalue":{"value":"http://jmlr.csail.mit.edu/papers/v19/17-283.html","type":"string"},"datatype":"url"},"type":"statement","id":"Q6829291$7A59F179-A4E3-4DF0-A4EC-DF94C4871A2A","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6829291$CDF046F2-E103-49C8-9793-4F1A46707450","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"6a9ff1a146ff44dca747e334413377c148d2df3d","datavalue":{"value":"60J20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6829291$7F0B39ED-C938-4D5E-87D9-322F88BADEE7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6829291$60AE6FC2-4E39-4100-B54E-12FEE1C5BC55","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"aa3ca91474fff28e420d9cace433f8447ec799b0","datavalue":{"value":"90C39","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6829291$EA06613E-2505-42B8-8D82-9AF24EE85CEA","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"0e8f6ebc5270f630b889b2d09cb24cf6b0416887","datavalue":{"value":"6982339","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6829291$6B2107E8-263D-4AEA-A5C8-2B503F6ABF54","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"a8cfb635100bcc8a85463e6beac1ce534f15033d","datavalue":{"value":"Markov decision process","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$502C8C3D-F7E0-480D-86BD-BF15E0AEA8CB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"c24907e29c5500b47e1335732316daec83c7635f","datavalue":{"value":"approximate policy evaluation","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$9CF04015-BB73-4F8F-9403-53EB452C5C8D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"8878e9443f4a387ef52f3ae3eaab062b33ea1670","datavalue":{"value":"generalized Bellman equation","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$608AC5F1-C5A8-4AFD-8874-A328DE5AFDFB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$7084BF41-EC28-44B5-8C2B-35D977921BB9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"c42e45a6d4b768e12b9c4d8d1da94bc35b153bba","datavalue":{"value":"temporal-difference method","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$509EDA2B-0A71-4661-A307-4F5E00E5CC31","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"397d9252ef89819a92633d8502b4000f6e56c083","datavalue":{"value":"Markov chain","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$2323EED7-EBE3-4887-B93D-8373FF29B346","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"2d1ef0a2396897c6b8c76bc8e55af3c9156dc745","datavalue":{"value":"randomized stopping time","type":"string"},"datatype":"string"},"type":"statement","id":"Q6829291$F918592E-912C-4C34-B100-2DEA6181A0C2","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":"Q6829291$46C3870C-F57B-4F34-A569-27851C7349E1","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"On generalized Bellman equations and temporal-difference learning","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/On_generalized_Bellman_equations_and_temporal-difference_learning"}}}}}