{"entities":{"Q2705757":{"pageid":2716502,"ns":120,"title":"Item:Q2705757","lastrevid":82798925,"modified":"2026-05-06T22:05:35Z","type":"item","id":"Q2705757","labels":{"en":{"language":"en","value":"Relative value iteration algorithm with soft state aggregation"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 1578372"}},"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":"Q2705757$B4F0CFF6-EC6C-4F94-9853-DCD654A9BADA","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"1295a1a3eb3184ff0f51187e71217ae32b3139b9","datavalue":{"value":"0966.93110","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2705757$7CE54B5D-06B9-40E1-B222-F47DE7781C57","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"41f1c493a3db1f8fb1e0d72536c597412f6fd738","datavalue":{"value":{"entity-type":"item","numeric-id":1913924,"id":"Q1913924"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2705757$DCA72E85-DE57-49F9-9E12-47C80AAD72B7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"8df0a5d732ccf0bd1bfcf1280e64ca64d755f629","datavalue":{"value":{"entity-type":"item","numeric-id":2704477,"id":"Q2704477"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2705757$756B5E95-4DD2-4179-AE77-63FF14FF2A9B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"40920eb28f1282d301624d22af56e582f2fc89da","datavalue":{"value":{"entity-type":"item","numeric-id":207172,"id":"Q207172"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2705757$21F57509-03B0-487B-A71D-14EE2DB3F303","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"bc7793238eb14ba137de9b73e7c0cd32610d70ec","datavalue":{"value":{"time":"+2001-08-01T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q2705757$3B824056-DA93-4223-A034-6F144EB9F27D","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"e3bc6c7cda8279d6ad2b578e7a7e4967447c3cc4","datavalue":{"value":"93E20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2705757$DF12D7CE-53CE-4BCB-882D-C78444942512","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"bd87a0473bfa14f58600a7b373a6a1e6cb1f2980","datavalue":{"value":"93A15","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2705757$ECC8B53B-0A60-4AE0-89EF-155991705BFD","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"121b58ae6a7b212ace67fd21bc62c475f760bc94","datavalue":{"value":"1578372","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2705757$FDF4DFD0-4DCF-442B-A230-728E3D6DDFE9","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"5c6b465da0b3066f8f95f845adce0a473abf5a2b","datavalue":{"value":"optimal stochastic control","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$29C49F08-7669-430E-A494-EB5D5302421E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"0d82cfa81638332a8c825bcbbd9d7f7f9c0c45be","datavalue":{"value":"dynamic programming","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$0824FA35-F1C0-4672-8EE4-2423A4805D71","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fbd1f99995fb6a13da62a377ba6327166316e976","datavalue":{"value":"Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$9144A6EE-CAAF-4D91-8A05-27A9DAEC6B1B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b5e274a96963dbfc74ca063bead992519a554dab","datavalue":{"value":"state aggregation","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$F9CB261D-8EE9-4D9D-A674-8B462D334E18","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"38674e8e1ce5bb22ccdaa70cce2bbc1937d495df","datavalue":{"value":"compact representation","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$A9A8D238-4C6E-41AF-93AF-67C7CB8896B1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"060744e4c1468dc387dc685cf778b4e49df56442","datavalue":{"value":"value iteration algorithm","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$36905CF6-1460-4C20-ABA1-A1578DE9DFAA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"4605262f950382e87dc58df46038532164191769","datavalue":{"value":"contraction","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$8A897B64-8DF8-48A7-858D-7E0D0F1FC83F","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":"Q2705757$2F287B41-11AF-4B4F-8921-730838C0E68F","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"02f12b4d160fad92ee4ad91b61039da4b01fe8c6","datavalue":{"value":{"text":"Relative value iteration algorithm with soft state aggregation","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q2705757$8D37523E-E267-4898-9681-4224C3CE21B3","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"35d9a317d2a205b03258f79c36e13734455cee47","datavalue":{"value":{"entity-type":"item","numeric-id":6768065,"id":"Q6768065"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2705757$3C1972AA-FEAF-4E53-97CA-157546E1A099","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"604b9baa3598a0d6535053ee16d8d46a73d1828e","datavalue":{"value":"A straightforward way to dispel the curse of dimensionality in large stochastic control problems is to replace the lookup table with a generalized function approximator such as state aggregation. The relative value iteration algorithm for average reward Markov decision processes (MDP) with soft state aggregation is investigated. Under a condition of contraction involving a semi-norm, the convergence of the proposed algorithm is proved and an error bound of the approximation is also given.","type":"string"},"datatype":"string"},"type":"statement","id":"Q2705757$9AE57CFA-00D2-4E34-BE53-57AE645462A5","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"6827de8b88468aad2c82107e1b61db0181f2e14d","datavalue":{"value":{"entity-type":"item","numeric-id":702619,"id":"Q702619"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2705757$C3FFA03A-9982-4609-8A3B-A8F7A9BB35C8","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"ad4c1bb3f1565dee64b1eae73c4912dd6b94323d","datavalue":{"value":{"entity-type":"item","numeric-id":5387976,"id":"Q5387976"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"5cd0a4c1432266517ecd34925b9ecadeff4d50c3","datavalue":{"value":{"amount":"+0.777044951915741","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":"Q2705757$80F69C0E-FDB3-456B-ADA8-3EA0DE21799C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"bbbf5d7c72c755e2222385b384e4208ad3081d74","datavalue":{"value":{"entity-type":"item","numeric-id":1066821,"id":"Q1066821"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"2025812a966bb0f6075c5a2956313b612d752a23","datavalue":{"value":{"amount":"+0.77447110414505","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2705757$D1861ACD-6574-4176-A41D-2AE376F6001B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"e7ddabf76d84ca181debb745fcee6e4c80a7c182","datavalue":{"value":{"entity-type":"item","numeric-id":2753225,"id":"Q2753225"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0f362bc2f7ec4498e907484eb42ba06ca9d8e139","datavalue":{"value":{"amount":"+0.7728242874145508","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":"Q2705757$CA22CD46-53D0-4604-AA05-DE966BC98D72","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"d808e80366dbecea61106f7ce184eb36ecb2cadd","datavalue":{"value":{"entity-type":"item","numeric-id":378753,"id":"Q378753"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0f362bc2f7ec4498e907484eb42ba06ca9d8e139","datavalue":{"value":{"amount":"+0.7728242874145508","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":"Q2705757$21E20C88-50EC-4F4A-8660-D20BBE86FC41","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"0bb4b180ae01ee68a5083c32db1975f7b676e79e","datavalue":{"value":{"entity-type":"item","numeric-id":1990495,"id":"Q1990495"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"8535a758a83e52849c98823bddeefac7c407b80b","datavalue":{"value":{"amount":"+0.7666627168655396","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":"Q2705757$5E21EE45-9D33-4BB9-B51F-AA11080BA7D0","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Relative value iteration algorithm with soft state aggregation","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Relative_value_iteration_algorithm_with_soft_state_aggregation"}}}}}