{"entities":{"Q1076618":{"pageid":1087370,"ns":120,"title":"Item:Q1076618","lastrevid":66693819,"modified":"2026-04-12T12:07:00Z","type":"item","id":"Q1076618","labels":{"en":{"language":"en","value":"Monotone value iteration for discounted finite Markov decision processes"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 3954679"}},"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":"Q1076618$1894858C-71DB-4F3C-BE38-7F57B2049515","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"5e179eb3f9745f7824010103d3f3b832d7403b0e","datavalue":{"value":{"text":"Monotone value iteration for discounted finite Markov decision processes","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q1076618$1115D918-17DA-4C5D-AE5E-09B7081871A9","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"dbf1aea627903e3ffb227578e749e4edf2783cff","datavalue":{"value":"0593.90084","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1076618$4FB80C55-C190-4E8A-BA31-66247E56CEF4","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"3c45fcfeab576dfacb6e2613866b4036a23dd65d","datavalue":{"value":"10.1016/0022-247X(85)90152-0","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1076618$458F351C-2522-482B-87D0-6CCB36FBEC36","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"c5ad7b9baf8e531c6b1ad954eb5f2899cc8fe5e5","datavalue":{"value":{"entity-type":"item","numeric-id":85344,"id":"Q85344"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$A52A3793-B259-457E-97FD-BDFEFBEF7546","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"3c94df5c9af0ede578c52141befd29044de13172","datavalue":{"value":{"time":"+1985-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q1076618$6CC46173-FB34-4B0D-827F-97B989A68218","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"f689feec645bf9b07902ac042d65a19e5a605cc0","datavalue":{"value":"This paper considers the properties of two modifications of the value iteration scheme for a finite state, finite actions Markovian decision process with the total expected discounted reward criterion. The first variant replaces the discount factor appearing in the value iteration scheme by a magnitude which depends on the results of the previous iterations. In the second variant some perturbation is added to the value vector on each iteration. The author shows that for some choice of the parameters of these methods they converge monotonically to the optimal solutions. He also presents some examples in which these modifications perform better than the usual value iteration scheme.","type":"string"},"datatype":"string"},"type":"statement","id":"Q1076618$EFF0707B-918C-48A6-A755-C78331182C25","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"0c39b36a1731e4259f3d83de96db84384ef191dc","datavalue":{"value":{"entity-type":"item","numeric-id":532680,"id":"Q532680"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$8A61CF93-71BA-4158-B777-D881A433EF79","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1076618$D96D10DE-9312-4993-8AB5-6E4D768C7DC5","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"ebe81eb6270780e4b912a58c34234ce1f0662db1","datavalue":{"value":"3954679","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1076618$A91C71FD-1E03-47FC-BDE8-B42BBC1D7DD8","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ef3d283103ac31175545b3fd6e9ad252c8dba3b6","datavalue":{"value":"value iteration","type":"string"},"datatype":"string"},"type":"statement","id":"Q1076618$5DBB2AC2-F055-4B3D-90BF-DD0BC55BE9B7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"6d72a6f5c746ddc4e751f0cbe99091f1f426ace5","datavalue":{"value":"finite state, finite actions Markovian decision process","type":"string"},"datatype":"string"},"type":"statement","id":"Q1076618$B237EC7D-E7D7-48B0-927D-CE9BC1CCCA1C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ca25de6696951a3a77df2f3fb54595724e7c8150","datavalue":{"value":"total expected discounted reward criterion","type":"string"},"datatype":"string"},"type":"statement","id":"Q1076618$C214B605-8C7E-4129-9771-EC4ECC2B73E2","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"14fb6158c2e7a30d22594a5ac8edc4708d1a10b2","datavalue":{"value":{"entity-type":"item","numeric-id":181183,"id":"Q181183"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$4E284C22-8273-4F2C-9492-59EEF3BF1C71","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":"Q1076618$95B64CF9-FE02-4B10-96CD-C72664091749","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"9039c63560118f49c65f860b1a4c794c8e620067","datavalue":{"value":{"entity-type":"item","numeric-id":3867541,"id":"Q3867541"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$4FCF4F59-8A30-4D3F-9D12-7118C0B7A5DE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"bbcc82ee2be8c39df26d83a7327b6f0f3bd10a36","datavalue":{"value":{"entity-type":"item","numeric-id":1216364,"id":"Q1216364"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$C76B7E3F-ADCC-4536-8487-6E284E280FC4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"97de10e970aa5dd2460b261f0f66327d1c6c8f26","datavalue":{"value":{"entity-type":"item","numeric-id":4045930,"id":"Q4045930"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$1B0BCFD0-B053-423B-9C40-59DF46D5BE44","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8d0c83891471dda42666bed3037f7d6a19c11e2d","datavalue":{"value":{"entity-type":"item","numeric-id":3856450,"id":"Q3856450"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$78AAB96A-9836-4D56-9399-35F1FCF380F3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"3e91905dee768b6da63d1083ab023af9e29922cc","datavalue":{"value":{"entity-type":"item","numeric-id":1136706,"id":"Q1136706"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1076618$11D20723-148F-4A4A-A596-800FE101A365","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"1a0b31acca258830d14f10c4570af9546763d6c7","datavalue":{"value":"https://doi.org/10.1016/0022-247x(85)90152-0","type":"string"},"datatype":"url"},"type":"statement","id":"Q1076618$07A57712-EC9B-402C-80E6-A9C4A8D7A174","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"37bc240106288ddca321b6282875a9b58bf1b2b0","datavalue":{"value":"W2066040239","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1076618$52F975E8-BBDB-4C20-AFBB-D3BEDE797381","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"7df7b20e132c80913e419ba7b195867d3416d163","datavalue":{"value":{"entity-type":"item","numeric-id":1323884,"id":"Q1323884"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"b68fc8924a8b817c85470670ea5a7d49a9a92374","datavalue":{"value":{"amount":"+0.8443040251731873","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":"Q1076618$1F02DE70-AF8B-4B74-A37A-41CF9FA607AD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"0277cc46ea8b2de78f6a27555b849d0dd4e20d3b","datavalue":{"value":{"entity-type":"item","numeric-id":4319773,"id":"Q4319773"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0a4121d5dda9493bdccae3fceb7df2561d75ba70","datavalue":{"value":{"amount":"+0.8336214423179626","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":"Q1076618$7A79F217-3922-4557-A9CB-492734F812CF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"819fe600bea22baea214d5f846273a4c27625ec3","datavalue":{"value":{"entity-type":"item","numeric-id":3984139,"id":"Q3984139"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"9d1a72e52b71a8ccf3283026852191d66d9b9d23","datavalue":{"value":{"amount":"+0.8323020935058594","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":"Q1076618$5F72A774-7B96-4E95-8390-495D50801FBD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"9978b8d6c32f5619a09e0a99ef0c58e84f6adbcb","datavalue":{"value":{"entity-type":"item","numeric-id":4293291,"id":"Q4293291"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"7858a8295fde6f0e1734bcff76f7840019bc391b","datavalue":{"value":{"amount":"+0.8229511380195618","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1076618$D0FD1BDC-C400-4A7D-87AA-6C20F0E31677","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"477980383cda967f077137bb76b17c669a88df58","datavalue":{"value":{"entity-type":"item","numeric-id":3691443,"id":"Q3691443"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"c00c7aa693524d43ef3b88e6b7522be6d2883df1","datavalue":{"value":{"amount":"+0.8197171688079834","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":"Q1076618$07E4725C-AC7D-4B53-960B-DF06006F35D2","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Monotone value iteration for discounted finite Markov decision processes","badges":[]}}}}}