{"entities":{"Q6149409":{"pageid":13283716,"ns":120,"title":"Item:Q6149409","lastrevid":94216577,"modified":"2026-06-05T06:14:36Z","type":"item","id":"Q6149409","labels":{"en":{"language":"en","value":"Neural Temporal Difference and Q Learning Provably Converge to Global Optima"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7812937"}},"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":"Q6149409$B5A0EA37-BA21-4BB0-9492-376DBEB9204B","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"9cf18f9c1f8637bdb0532e983de94522ea823222","datavalue":{"value":{"text":"Neural Temporal Difference and Q Learning Provably Converge to Global Optima","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6149409$9FCAD5F3-F46F-43C0-90B0-BAADF88E0EE7","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"74d5e3f6644be5fb9c7e80443c81907961bfd0e7","datavalue":{"value":{"entity-type":"item","numeric-id":2193793,"id":"Q2193793"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6149409$8824D944-911F-4EEB-88FF-0D8958CD76E7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"b8bb31534aaff78fdad2e17338db5fab9c006bd2","datavalue":{"value":{"entity-type":"item","numeric-id":2032182,"id":"Q2032182"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6149409$2699F898-30A3-4A9F-BAAF-FF3CF814FF1D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"5ea6e5c853f3064c2c45507b7a82fb6ab6bdb461","datavalue":{"value":{"entity-type":"item","numeric-id":292862,"id":"Q292862"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6149409$B195788F-F65A-4C3B-ACC1-32625044C173","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"408f76542a47926032d44b21fff6d73648805442","datavalue":{"value":{"entity-type":"item","numeric-id":482872,"id":"Q482872"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6149409$191D19C9-EBC1-4675-8CEA-9958F846E34E","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"cccce4a4205b51ff587d222bc7a07ed4bfa86d8f","datavalue":{"value":{"entity-type":"item","numeric-id":103831,"id":"Q103831"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6149409$8B2917F7-2C17-4221-92C3-7DB70741BA1C","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"c36f49e8b4c980a4dd1d9ff655af85a597603033","datavalue":{"value":{"time":"+2024-03-05T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6149409$2083B135-B993-4ACB-982D-E701833D0993","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"13009102684b77779d53f5dbf201f09f77b9bb37","datavalue":{"value":"https://arxiv.org/abs/1905.10027","type":"string"},"datatype":"url"},"type":"statement","id":"Q6149409$76E22435-F6CD-4A65-85BE-620A27D7D23C","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6149409$0BDC2747-1A25-47F5-A734-098D3ABEE3CD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6149409$C6A6F8B4-ECBC-4AFE-AC7E-CC18D994126B","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"50a0c5b344e9c2f7ad2238fad336356d9f7652bb","datavalue":{"value":"7812937","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6149409$E21E1AF4-71E1-446A-8230-42ECD4BDA9CA","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q6149409$9DE44F2F-DC08-4511-BF34-CFD88D4B87A7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"a0d39709e16719b89fc1d325a47ee6170e462160","datavalue":{"value":"temporal difference learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q6149409$F476B590-31BE-4635-8CD6-65B1CA9F1610","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"6fa6e74d1978249a605e84a0a4a8a65f39174c6b","datavalue":{"value":"overparameterized neural network","type":"string"},"datatype":"string"},"type":"statement","id":"Q6149409$FC3F1D81-2E02-4817-97A3-4D1727FDFAFE","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6149409$A40463DC-DEF8-412F-B1C8-FFC19A11A9FA","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"e3bdefa6902eba1730664815821774757da8ba68","datavalue":{"value":"W4367298527","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6149409$E083298C-F8E9-4C58-BD67-197A294873FB","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"279eb1ce3d659829ade9337212b6cb5205869b74","datavalue":{"value":"10.1287/MOOR.2023.1370","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6149409$453682AC-6600-4FC1-905A-C1E6D9DAA414","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"a801c29d50c9fab3f3eae3ea93d463884b0c75d2","datavalue":{"value":{"entity-type":"item","numeric-id":5162625,"id":"Q5162625"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"f0f2e1418e866e1fa7a8d71d02a0dcb9f47f6830","datavalue":{"value":{"amount":"+0.7619828581809998","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q6149409$D841E0B9-D206-4ABA-97FF-F55F834F64BC","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"faf59e9a2a542e5b797567ea67e1e81fffb07de5","datavalue":{"value":{"entity-type":"item","numeric-id":5003727,"id":"Q5003727"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0194c6aefcd0e2f1c6fab9ddb5ce01acb37b2a3b","datavalue":{"value":{"amount":"+0.7541861534118652","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q6149409$FE1C6184-6CEB-44D9-A00E-5B8F6DAA7AA6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"49c98e02597b76cfa1a5e2875bddc32216c3b39f","datavalue":{"value":{"entity-type":"item","numeric-id":1812934,"id":"Q1812934"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"2d3d0c9d2bd6cddf12bc1bd8845ccece814945e5","datavalue":{"value":{"amount":"+0.753794252872467","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q6149409$1E1A01A4-A69E-4069-A830-A83E04EDD729","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"58d83d0e5018ac0ba8f80a1415997c1046e63c6e","datavalue":{"value":{"entity-type":"item","numeric-id":4558791,"id":"Q4558791"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"ba9bf4dd91606274f7f8f6aee5296e9fac97208e","datavalue":{"value":{"amount":"+0.7480029463768005","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q6149409$E593183B-9A00-420A-86F6-65FEF05943DC","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"d1c4212e5afbe535c7026d800ae2553f239cb0a0","datavalue":{"value":{"entity-type":"item","numeric-id":5928992,"id":"Q5928992"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"df09dcd221e6553b24a57846e7c219f4499beee2","datavalue":{"value":{"amount":"+0.7422963380813599","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q6149409$FC757C04-B3A0-44F9-BA08-42F02AF49401","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Neural Temporal Difference and Q Learning Provably Converge to Global Optima","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Neural_Temporal_Difference_and_Q_Learning_Provably_Converge_to_Global_Optima"}}}}}