{"entities":{"Q2711577":{"pageid":2722316,"ns":120,"title":"Item:Q2711577","lastrevid":82875431,"modified":"2026-05-06T22:19:42Z","type":"item","id":"Q2711577","labels":{"en":{"language":"en","value":"A learning algorithm for discrete-time stochastic control"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 1591175"}},"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":"Q2711577$378E806B-6041-4C85-BDE5-C9199102B74D","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"366ce56d3b52446838c9e8125b2a236afbb53c4d","datavalue":{"value":"1029.93065","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$B183711E-501E-40B0-99F8-EB734EC9E9CD","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"2f8e0f3bb8f297dee76b8dc550094a2df21d4168","datavalue":{"value":"10.1017/S0269964800142081","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$C13FF768-FAFA-4DC4-BAB3-521C6CB47077","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"814a9085f4d809332ee2d2025568b98a08f25a9b","datavalue":{"value":{"entity-type":"item","numeric-id":203041,"id":"Q203041"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2711577$3BC9F80E-B533-4EA2-8E83-5A36D6455C39","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"0c6f2d67ee4e005036b68423270bd3eb51d5390d","datavalue":{"value":{"entity-type":"item","numeric-id":2709773,"id":"Q2709773"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2711577$866DE358-566E-4914-B9F5-F350E264CA6C","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"a0ee4604569c57825e851b24a6d04754ea6fd6e6","datavalue":{"value":{"time":"+2004-02-02T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q2711577$D6ACD2AF-C2BB-45D0-B51F-E71CBB877362","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"4fd8d49a375e8786d86b39f94e9773f56a9b1c4e","datavalue":{"value":"93E35","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$03ACC38D-7FBA-4403-9391-B090893F44BE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"559e9e993b5739992d837c78bb1ff74a483fa093","datavalue":{"value":"93C10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$DD0BB309-DEA4-4229-A618-BFEEDBFA3D1F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"39a0025ac480893a6c3723330b06364463bbd01f","datavalue":{"value":"93C55","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$DA3EEA9C-80A5-456A-8FBD-50220DA91CD7","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"66f2de47d1c403dfb9beb24ceb70fbf1130497ab","datavalue":{"value":"1591175","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$B66EB6DC-1FD3-4101-9457-5AD883341B35","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"1099d3774835e99f71b0be7ad3c7400fded8078a","datavalue":{"value":"nonlinear control","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$9AC00796-C693-43CC-B19A-21F80FD39AEB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"cfeaa132e0d4a1e3a29f660196eb2ab048854605","datavalue":{"value":"\\(Q\\)-learning algorithm","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$BF6BF176-EA01-408D-A079-DF920FA2A2F2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b694bcfd5ee9a0df02e741c92a361373bf54032b","datavalue":{"value":"compact state space","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$E3A0D6CA-ADEE-420A-A6D8-F74AADDE95BF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"93349987a25f5f3b27560937df2f3c5734d7b523","datavalue":{"value":"compact action space","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$073059B8-E301-4AF0-B2C8-DC9D44D16A69","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"98473aa66f09199fde86211e0ebae35d1ad7b7ef","datavalue":{"value":"simulation based algorithm","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$0DACB776-EF5C-4DA8-83DC-E0444C4154D3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"05ca76faeb672415cff41bbc3ad8454e227be1fa","datavalue":{"value":"learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$587EA6F3-A8D5-43BD-8D8E-6CCE869270CD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"715b2a8b4b33c75f8fca520f419d78856a6ad273","datavalue":{"value":"discrete-time stochastic control","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$8DC3937B-B26D-4F12-AE74-46BF16D4F924","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"baed917af91ddf2ea67ba33d7510b901590d4d96","datavalue":{"value":"almost sure convergence","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$175EFDF6-41FE-4B6D-8EDA-8E70B5E63B81","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":"Q2711577$596B98BE-B7D1-4A7E-A4C4-6B475FBED39D","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"3cc8df43ac7126f13c6cb0e4928a395a32d57c49","datavalue":{"value":"https://doi.org/10.1017/s0269964800142081","type":"string"},"datatype":"url"},"type":"statement","id":"Q2711577$D11A6AC5-0DAD-406E-B356-03F6393A8AB6","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"43cee8f17e7859ac0f3d604fc2b014fee8fdad7a","datavalue":{"value":"W1965413238","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2711577$07AB431A-2D33-40D1-9AAC-983E2590C1A3","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"246f723228cba5341455b9a0171da5b333586eae","datavalue":{"value":{"text":"A learning algorithm for discrete-time stochastic control","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q2711577$02928734-FCDD-4003-92DE-349212E11C9F","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"3ac783ebe47925af37e49f2cfb86f63ede0cf44d","datavalue":{"value":"A simulation based algorithm for learning ``good'' policies for a discrete-time stochastic control process with unknown transition law is treated with the state and action spaces both being compact subsets of Euclidean spaces. Under suitable conditions almost sure convergence is proved. The paper is in the spirit of \\textit{W. L. Baker} (PhD. Thesis, Harvard University 1997), but it analyzes the full nonlinear case and is in the tradition of the ordinary differential equation approach.","type":"string"},"datatype":"string"},"type":"statement","id":"Q2711577$9CFA912D-FD0D-48AD-BA4F-C44F805F80EA","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"fe6c178ba631c829fb2983f173fd8079aee474f5","datavalue":{"value":{"entity-type":"item","numeric-id":590466,"id":"Q590466"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2711577$804BD135-1F46-41E5-BB48-EF79191CC82B","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"023c4208343604e7da2cba7b31e4c2a513a72537","datavalue":{"value":{"entity-type":"item","numeric-id":4540476,"id":"Q4540476"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"70766a4fccad6b3aec675aaabb93e814454d67cc","datavalue":{"value":{"amount":"+0.8014315962791443","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2711577$EE8AC62E-5DCC-4A7C-94DC-1B84969AFB0F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"5b6584600e54a34b3a4387b0242479460e465f7f","datavalue":{"value":{"entity-type":"item","numeric-id":4228400,"id":"Q4228400"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"ab4da67103000e8615b2f7d77baab4dd4ea3d134","datavalue":{"value":{"amount":"+0.7993116974830627","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":"Q2711577$86FDED4B-4E26-4C5D-8D87-F486BA3564CF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"9bba07870f0e8c6a12c4e7012ebd56b764b04b8b","datavalue":{"value":{"entity-type":"item","numeric-id":4540401,"id":"Q4540401"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"55dcd36a9350c67e5d0ee39e56c4cfe1f1565500","datavalue":{"value":{"amount":"+0.7973366975784302","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2711577$E8A5EA3A-122E-4162-8936-5A7534A13D1A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"8cfa4166788ee87fad21f6c134c4511f9efa6eb8","datavalue":{"value":{"entity-type":"item","numeric-id":5093265,"id":"Q5093265"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"ebb0da1b670bf47929e4cbc9164b94237bef50cb","datavalue":{"value":{"amount":"+0.7915440797805786","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":"Q2711577$1172110B-D331-4514-93CA-BF0224E0F8AE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"bc47b6b6955fa63cc5fd16c3721263a920d627ee","datavalue":{"value":{"entity-type":"item","numeric-id":3830898,"id":"Q3830898"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"65fabe5162a35625539b3c4fcc40eaf0e0933388","datavalue":{"value":{"amount":"+0.7903698682785034","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":"Q2711577$61BCE795-CD44-4ADD-A504-E817D23F1480","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"A learning algorithm for discrete-time stochastic control","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/A_learning_algorithm_for_discrete-time_stochastic_control"}}}}}