{"entities":{"Q832436":{"pageid":834284,"ns":120,"title":"Item:Q832436","lastrevid":64710441,"modified":"2026-04-11T21:43:09Z","type":"item","id":"Q832436","labels":{"en":{"language":"en","value":"Optimal control with learning on the fly: a toy problem"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7498312"}},"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":"Q832436$0403F549-9BB2-4FAC-9B3C-7A81430E9120","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"e469e23c9f12135bf69e2a8c5cec2c1313f3b367","datavalue":{"value":{"text":"Optimal control with learning on the fly: a toy problem","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q832436$910162A7-CD9F-46EA-BC73-0D6184F51800","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"54408a0cc71b4e1ac4a812e17f8a25d04455b790","datavalue":{"value":"1485.93628","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q832436$3EC57C01-40A0-468D-9F20-58E266554840","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"d33dc1833dda69ff1169b2fd13b4339df578a0e2","datavalue":{"value":"10.4171/RMI/1275","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q832436$D5FC8664-87AA-438C-AFEF-EAB998370026","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"3872f78d3e94002c429d382a535df1110cda4a9e","datavalue":{"value":{"entity-type":"item","numeric-id":832434,"id":"Q832434"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$C90E62D4-CF44-4349-945F-18B21B906F2F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"abb04ae701e48c6009b91621e0778a62bb19152b","datavalue":{"value":{"entity-type":"item","numeric-id":317183,"id":"Q317183"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$C78D52BD-CBF0-4260-9604-F032D7726EDA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"855948d565d446e1d9e8fa65b2b93be6753aa41b","datavalue":{"value":{"entity-type":"item","numeric-id":832435,"id":"Q832435"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$7D96AFEA-DC58-48FF-83D4-B0E1C4E0CD52","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"121e5f7d0994874c36647ddea06b507c453289c1","datavalue":{"value":{"entity-type":"item","numeric-id":495895,"id":"Q495895"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$F59409DF-EE39-4AE5-8BE2-41173E088063","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"4eb7cc1856a305a963c7393d6ad45e329f3b5d88","datavalue":{"value":{"entity-type":"item","numeric-id":170748,"id":"Q170748"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$E68EEDB0-B93E-4110-BB37-0E445BF8BB86","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"26426ab4d5a6ecfa201abc41ba9257e3996155a5","datavalue":{"value":{"time":"+2022-03-25T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q832436$408913E3-AA59-4B74-BDFC-6305B15A8368","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"4f2cee90c8b9a9a3cb9b370d3ba4b56de8c340de","datavalue":{"value":"https://arxiv.org/abs/2002.11578","type":"string"},"datatype":"url"},"type":"statement","id":"Q832436$F7844227-7241-4E9A-A3B5-96A4E2ED5BD3","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"50338eaa1c8482769df5c55af715764287d4a7b0","datavalue":{"value":"Summary: We exhibit optimal control strategies for a simple toy problem in which the underlying dynamics depend on a parameter that is initially unknown and must be learned. We consider a cost function posed over a finite time interval, in contrast to much previous work that considers asymptotics as the time horizon tends to infinity. We study several different versions of the problem, including Bayesian control, in which we assume a prior distribution on the unknown parameter; and ``agnostic'' control, in which we assume nothing about the unknown parameter. For the agnostic problems, we compare our performance with that of an opponent who knows the value of the parameter. This comparison gives rise to several notions of ``regret'', and we obtain strategies that minimize the ``worst-case regret'' arising from the most unfavorable choice of the unknown parameter. In every case, the optimal strategy turns out to be a Bayesian strategy or a limit of Bayesian strategies.","type":"string"},"datatype":"string"},"type":"statement","id":"Q832436$0A85ED06-C03A-42CC-8A5D-DDFF1566624F","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"e3bc6c7cda8279d6ad2b578e7a7e4967447c3cc4","datavalue":{"value":"93E20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q832436$A73E1EE7-1482-4597-B382-F88F2EA34200","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"f0d0d77898e985e192355ef3ba3239802f14bb8e","datavalue":{"value":"7498312","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q832436$5943977E-1A21-40BF-9DBA-EFBD52846F38","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"af637498c021118a08b6b4f4d04cef45ea88a21b","datavalue":{"value":"regret","type":"string"},"datatype":"string"},"type":"statement","id":"Q832436$B58F3DF1-A640-430C-B104-CD3B9DF61BAB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"56d85aa22959094ecc003ac28085d2ab6f8f44c0","datavalue":{"value":"competitive ratio","type":"string"},"datatype":"string"},"type":"statement","id":"Q832436$266F4C99-4EBE-4C84-BE4C-142856150E4E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"5b1bc4dce50777e05ab9cb1388520764604da11f","datavalue":{"value":"agnostic control","type":"string"},"datatype":"string"},"type":"statement","id":"Q832436$DB036D84-617F-407B-835A-AF95CF0D3CA0","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b253d7d94b74404330dfb928accbc7530cbafcd3","datavalue":{"value":"adaptive control","type":"string"},"datatype":"string"},"type":"statement","id":"Q832436$3E613397-2A62-4EB8-ACE1-D18F83CE86D9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fddbe89b6acc37b783af5e1dae0a05afaeec881a","datavalue":{"value":"fuel tax regret","type":"string"},"datatype":"string"},"type":"statement","id":"Q832436$508FD4A0-DB64-417B-91B3-2B450962B259","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$BFA81FDC-1CA1-4445-B4C1-3472BDB30FC1","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"e5314db28cbe3eb7bfca044b623c4acedcac4a8c","datavalue":{"value":{"entity-type":"item","numeric-id":5959973,"id":"Q5959973"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$5461452A-3B15-42FA-91A5-7398632BD809","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"67be9d8aae912907830f298fc6485c1dbd0ec6e7","datavalue":{"value":{"entity-type":"item","numeric-id":3376698,"id":"Q3376698"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$D571B1BD-161F-41D0-A054-FDED5C58C9F6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8327d1a8ee5e7e342b1214a8eb1f611a84d257f7","datavalue":{"value":{"entity-type":"item","numeric-id":5396763,"id":"Q5396763"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$E5F9CF2A-D54F-40FF-A14E-48E420BAC596","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"b193a85e64b8aa45a6a5205ad8fe538de425427b","datavalue":{"value":{"entity-type":"item","numeric-id":5470194,"id":"Q5470194"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$17D6ACD2-772F-4F62-B314-191FC59FE3C4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d0b556d51b5e676c221d0327f63920155af2c236","datavalue":{"value":{"entity-type":"item","numeric-id":1060517,"id":"Q1060517"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$80C0E072-7D6C-461F-895F-C63054CC56A1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"2029dc5ae6c8cae2492e7f284909e2f986c15910","datavalue":{"value":{"entity-type":"item","numeric-id":3091374,"id":"Q3091374"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q832436$7FD08B7A-70AA-4ED8-BF85-E3C93DA60AC8","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"59de987f44be8cbe616fa5e4a91d93b45fef1397","datavalue":{"value":"W3177406382","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q832436$C7DCBF8D-9C34-495A-B5C6-7479FFB0C0E0","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"b147bc9674d89b1a50edea7359f9a75bd9f82eba","datavalue":{"value":{"entity-type":"item","numeric-id":2692507,"id":"Q2692507"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"7368d7dceab2fa935419f05941fbc966fce432b1","datavalue":{"value":{"amount":"+0.8453490138053894","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":"Q832436$8588AC71-55B7-454D-BFFF-DC290EE74390","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"663543c237d3a6fd1028b2b7ef55a5046b141db9","datavalue":{"value":{"entity-type":"item","numeric-id":3832444,"id":"Q3832444"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"62deefcb23aa73444890ba8598031cdf053bf3a6","datavalue":{"value":{"amount":"+0.843239426612854","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":"Q832436$77783625-B04B-47E0-B590-C44F1303731B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"0d12d24ae487e6863de39e51df8c4b7152b02c93","datavalue":{"value":{"entity-type":"item","numeric-id":1605197,"id":"Q1605197"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"94cc72957c4f8670de5c66daad2651525bf46faf","datavalue":{"value":{"amount":"+0.7937319278717041","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q832436$C360AB2A-E4C6-4B98-8150-3B1995D252AB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"8c6a5057606538fd9896a0e5745aa88fd6f2d9c7","datavalue":{"value":{"entity-type":"item","numeric-id":3435945,"id":"Q3435945"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"d24b533cf9a5519399b3c15e69fb19c8c125ee33","datavalue":{"value":{"amount":"+0.781589150428772","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":"Q832436$348DA8D2-C3C9-4E2A-88BA-8564AF25CA77","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"847220105e92a6a4785ad69ceb80c9260fcb5325","datavalue":{"value":{"entity-type":"item","numeric-id":3974042,"id":"Q3974042"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"388cff4203fa67b4e5114a5c26dd99e0411b9525","datavalue":{"value":{"amount":"+0.7780045866966248","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q832436$B67BE702-0CBF-4115-9EAF-AB2A90E10D0D","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Optimal control with learning on the fly: a toy problem","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Optimal_control_with_learning_on_the_fly:_a_toy_problem"}}}}}