{"entities":{"Q1095048":{"pageid":1105800,"ns":120,"title":"Item:Q1095048","lastrevid":69627435,"modified":"2026-04-13T08:18:28Z","type":"item","id":"Q1095048","labels":{"en":{"language":"en","value":"A unified approach to adaptive control of average reward Markov decision processes"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 4027209"}},"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":"Q1095048$128D57D5-F74C-41EC-8248-50C05B72D9DD","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"7df40409ecc4d09b13ae22d8aa15494c9277ae3c","datavalue":{"value":{"text":"A unified approach to adaptive control of average reward Markov decision processes","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q1095048$A277F826-917B-4BF5-A99C-248476053C06","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"ff5d7c05b3ca61d32f8528870ff3e1966f78b72e","datavalue":{"value":"0631.90084","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1095048$13055C4F-C8B4-4A16-B194-70965725D8AA","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"2f7adda04b0063568f9f27b92341b85426e5456b","datavalue":{"value":"10.1007/BF01740510","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1095048$C87CA737-1D1C-4729-9C16-ED83066C388C","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"c3d6deb906a789c24c922a0a48fc44f9abd90f51","datavalue":{"value":{"entity-type":"item","numeric-id":1095047,"id":"Q1095047"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$0A7E732C-82BB-4C66-80B3-D2A3BE70BDF5","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"9c43b2600d1729fd3bff9a1684164aec83749349","datavalue":{"value":{"entity-type":"item","numeric-id":202828,"id":"Q202828"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$772816EA-468B-49B1-889A-5993578B85BF","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"31a1937240ca4a323604b4728c31d242b5596d7c","datavalue":{"value":{"time":"+1988-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q1095048$FD90613A-5F05-4567-823A-928A0DE1B445","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"2f2e7799f46ea8739b88a42e59d597da91422d0f","datavalue":{"value":"The paper presents a general optimization method for adaptive average reward Markov decision problems. Optimal decisions are determined by applying after each observation of the state and estimation of the unknown parameter a policy improvement step to an auxiliary value function, converging with increasing time to the true relative value. This method includes the classical procedure of estimation and control [cp. \\textit{M. Kurano}, J. Oper. Res. Soc. Japan 15, 67-76 (1972; Zbl 0238.90006), and \\textit{P. Mandl}, Adv. Appl. Probab. 6, 40-60 (1974; Zbl 0281.60070)], the nonstationary value iteration [cp. \\textit{A. Federgruen} and \\textit{P. J. Schweitzer}, J. Optimization Theory Appl. 34, 207-241 (1981; Zbl 0457.90083), \\textit{R. S. Acosta-Abreu} and \\textit{O. Hernandez- Lerma}, Control Cybern. 14, 313-322 (1985; Zbl 0606.90130), and \\textit{M. Kurano}, J. Appl. Probab. 24, 270-276 (1987)], and a lot of new procedures, too.","type":"string"},"datatype":"string"},"type":"statement","id":"Q1095048$CD50B14F-3D63-4B78-9A1E-5F86592E8576","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1095048$E27B8F51-8322-4D5B-A271-763504D8A11E","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"8ec6b076478bd050814c51b403ec3678cce2f119","datavalue":{"value":"4027209","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1095048$A1CA4CCC-B19A-41A1-BDF5-D7C1AEEBC03B","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b253d7d94b74404330dfb928accbc7530cbafcd3","datavalue":{"value":"adaptive control","type":"string"},"datatype":"string"},"type":"statement","id":"Q1095048$712EF5F6-D092-4FF1-A7C1-B59AD58E4A14","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"430825e77b9956e66e29d7888227ae24c896e19b","datavalue":{"value":"adaptive average reward Markov decision","type":"string"},"datatype":"string"},"type":"statement","id":"Q1095048$D214619D-F36C-4A05-8F05-B056C5263605","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"9fe5038e9ac1cfd432f1c835891b65c04b38db6e","datavalue":{"value":"policy improvement","type":"string"},"datatype":"string"},"type":"statement","id":"Q1095048$E08270F4-76B4-4CB4-BB3F-136DA99837FB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"57222b9db4d14d9e9d00aab7c3922637e87cfbcc","datavalue":{"value":"nonstationary value iteration","type":"string"},"datatype":"string"},"type":"statement","id":"Q1095048$53B1FDF5-43BE-47E9-8C7F-6511A8FB4692","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$E37FAB51-EB51-45C4-86F0-FB5BE489A8C0","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"21849b4567b3beb912fa6c9306855cee15638600","datavalue":{"value":{"entity-type":"item","numeric-id":3745652,"id":"Q3745652"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$4F39FC4C-852A-4E29-BE03-8C7DC3A9C559","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"ffeef91846331be9b6aaa2dd0bb28f82f294672a","datavalue":{"value":{"entity-type":"item","numeric-id":3313754,"id":"Q3313754"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$3E166513-9E4C-4B6A-87BF-FDC80EDFD632","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"5a04fea5e37537baa202e80f5831309f1960cbbb","datavalue":{"value":{"entity-type":"item","numeric-id":4168795,"id":"Q4168795"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$E261F4D1-703F-40D2-B6B5-BC95381EFC16","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":"Q1095048$7B32E03B-2EAB-4C8F-AA2F-8E019CC8E412","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"2469d5ab3a820ed397bb5ff822fbac7c077580bc","datavalue":{"value":{"entity-type":"item","numeric-id":1250794,"id":"Q1250794"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$933A3B73-F9AC-47A3-B18E-93BE98B15BFB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8e1935fd4a878e1bd2c24d1c5baa91d69399ac97","datavalue":{"value":{"entity-type":"item","numeric-id":796461,"id":"Q796461"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$6286AB5A-22F0-47AB-A67C-85B79B58AAAD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"f61b7c666ab612130480d5b119c135c2253271e3","datavalue":{"value":{"entity-type":"item","numeric-id":5599448,"id":"Q5599448"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$8B3FE49B-4A31-4FD8-AA3C-8DE96D756190","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"42d55da566aba351715c932ef88e440eb495bc46","datavalue":{"value":{"entity-type":"item","numeric-id":3879083,"id":"Q3879083"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$A1044799-0E4D-408F-956C-E0BFC5E8A6E2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"efb3cb5639bd4c6d48ec6d98465d59981a25a98d","datavalue":{"value":{"entity-type":"item","numeric-id":5649557,"id":"Q5649557"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$35DAE636-9C13-44DC-B9D4-45179ED9C1B7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"e4f9bd93966769995286ed826581fceba5b85e52","datavalue":{"value":{"entity-type":"item","numeric-id":3664853,"id":"Q3664853"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$F000ED56-B206-45D0-8270-E63F43C3F155","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"cee0a245c873abd9b1ffcf9e43458e656970dc4f","datavalue":{"value":{"entity-type":"item","numeric-id":3768706,"id":"Q3768706"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$B4CA0272-EBCA-42CF-93AE-AAE7BC83AA65","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d03948ad52d599b98e967d89cc9dc9ba0b54e770","datavalue":{"value":{"entity-type":"item","numeric-id":4766345,"id":"Q4766345"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$64F39F5F-EEB1-4EEE-A252-1AB5B775E795","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"f5ac96454912f41d8b153896a7aa97285c5bced5","datavalue":{"value":{"entity-type":"item","numeric-id":3881672,"id":"Q3881672"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$21345BA1-AF65-408A-AD90-CAD3EF1CF79A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"76d57dcb21d036296eb0a0afa1babad3e64f88d3","datavalue":{"value":{"entity-type":"item","numeric-id":4173220,"id":"Q4173220"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1095048$A6BC977D-08C4-4B6C-960C-2C92FDC98543","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"f6a99dfd1d43b81412fb94ecec44db3e9fcfab3f","datavalue":{"value":"https://doi.org/10.1007/bf01740510","type":"string"},"datatype":"url"},"type":"statement","id":"Q1095048$429B2E2F-2761-4DA5-A780-AEA81968EC53","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"8c67bfbb05a435e7622fed8cea3c2edc8082b5f6","datavalue":{"value":"W2319020649","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1095048$CA9C95AC-AD33-415A-8F7C-479CF1D2C3D1","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"2eee0222bb902c3afc133da158b8d992bfd98e5d","datavalue":{"value":{"entity-type":"item","numeric-id":2276895,"id":"Q2276895"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"999325fc1b5773e20eec90c91cf24244b18fe4a8","datavalue":{"value":{"amount":"+0.8871362805366516","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":"Q1095048$E538A962-DDC9-4B27-B670-520A9997B3D1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"3e3b31fbe75ce2213038a5b034182e7f074a0a60","datavalue":{"value":{"entity-type":"item","numeric-id":3772003,"id":"Q3772003"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"f6b0cb3b8b0a00098febf835dd6c094188487659","datavalue":{"value":{"amount":"+0.8700859546661377","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1095048$BDB1DB26-88B2-4EE4-9308-B681ED9E1F1A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"fe694cc87a7438e7a01a05c5ef93d94768f2bb41","datavalue":{"value":{"entity-type":"item","numeric-id":5688680,"id":"Q5688680"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"5c56d7dde711c4d974d1b2d931f0a4a71e07bb2a","datavalue":{"value":{"amount":"+0.8634220361709595","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":"Q1095048$DAEABE77-4E62-4B77-A97D-A18EDD59F65E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"b3aa758509f3fda272039f9b28fa3c322d25127c","datavalue":{"value":{"entity-type":"item","numeric-id":4339383,"id":"Q4339383"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"06186bdbb80d7cbe7d5656b913e9153615d4ba3a","datavalue":{"value":{"amount":"+0.8585073947906494","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1095048$CBF1FF51-7F95-4B84-A770-B5F39B1ACBA6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"83b2902ffea21ae7455192896e6ffc3ea4877f13","datavalue":{"value":{"entity-type":"item","numeric-id":4540356,"id":"Q4540356"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"e21b8e5471c54076491acaa280dc772b3204eb87","datavalue":{"value":{"amount":"+0.8561966419219971","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":"Q1095048$8BF5522A-2692-4606-AA75-206071CB98F6","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"A unified approach to adaptive control of average reward Markov decision processes","badges":[]}}}}}