{"entities":{"Q5955768":{"pageid":8132570,"ns":120,"title":"Item:Q5955768","lastrevid":47744062,"modified":"2026-01-02T14:16:57Z","type":"item","id":"Q5955768","labels":{"en":{"language":"en","value":"A tutorial survey of reinforcement learning"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 1706651"}},"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":"Q5955768$CD9BD0F7-A61A-4B03-A227-D675A530515D","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"37e08aa2606464b913e19c93dcc0a45668c6ea71","datavalue":{"value":{"text":"A tutorial survey of reinforcement learning","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q5955768$3E077952-4FF2-4C93-82C3-362839727413","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"b958e4ac525d58f2fa3046f6ba72a989b613e1c6","datavalue":{"value":"1026.93520","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5955768$8461A319-94AA-4778-8CF2-F42A80461A6A","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"74833b4fa6c9286192314b43d387deccc2526ba7","datavalue":{"value":"10.1007/BF02743935","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5955768$A38BA634-C1B7-4D0C-BEA6-9DEF4561DA52","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"1a947b5002a2baceed42c066548d81c4b38b3fdc","datavalue":{"value":{"entity-type":"item","numeric-id":229978,"id":"Q229978"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$92626141-E004-435B-8A25-2499C99F09B4","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"e53cf98f1180bc6cc83969e8a66733f9be7d258d","datavalue":{"value":{"time":"+2002-02-18T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q5955768$D9D6461B-FA61-43B4-A1C8-B7BC8B421821","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"179fdc1755a4c4afa0b2d7f0e56779c3c8681c08","datavalue":{"value":"Reinforcement learning (RL) refers to the process whereby a learning system learns an associative mapping by maximizing a scalar evaluation (a reinforcement) of its performance from the environment. Delayed RL is a process in which the environment yields only a single scalar reinforcement collectively. Such tasks arise in the optimal control of dynamic systems and planning problems of artificial intelligence. Here, the authors `provide a comprehensive tutorial survey of various ideas and methods of delayed RL'. The connexion with stochastic optimal control is explored, and differences between delayed RL and dynamic programming methods are discussed. Model-based and model-free methods are examined, and general issues relating to the practical implementation of RL algorithms are noted.","type":"string"},"datatype":"string"},"type":"statement","id":"Q5955768$5CC8A7DA-7474-4110-BC17-AD0E0E839578","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"cc9a6f3d7be5ebe71e033a336cb453bb8cdc5ae7","datavalue":{"value":{"entity-type":"item","numeric-id":1409254,"id":"Q1409254"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$DE8B06C0-3139-4E2A-9F6E-EB426CC9DAAB","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"4fd8d49a375e8786d86b39f94e9773f56a9b1c4e","datavalue":{"value":"93E35","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5955768$6DBD04E9-26FF-4A1E-84E1-0B214151DDA7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5955768$C6C9AEE9-8608-4616-8615-64E469195806","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"1c903d4b9fb154111bcde1e07d1b5085ee3e3e47","datavalue":{"value":"1706651","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5955768$8618DA24-4E82-45F1-B379-114B18797418","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q5955768$D30E374B-B3DB-4B07-A9B5-C18B9250CB28","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"0d82cfa81638332a8c825bcbbd9d7f7f9c0c45be","datavalue":{"value":"dynamic programming","type":"string"},"datatype":"string"},"type":"statement","id":"Q5955768$2A73290C-01FB-48BC-B158-C75192671421","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"f47fee90c5592664decba5aa2e51ae852ecd7730","datavalue":{"value":"optimal control","type":"string"},"datatype":"string"},"type":"statement","id":"Q5955768$EA2D1A56-DC78-42E8-B415-EC2A34ABE775","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b0efe91da4df536f9ec53a9f276b6c2c113d29db","datavalue":{"value":"neural networks","type":"string"},"datatype":"string"},"type":"statement","id":"Q5955768$9DAF9BD6-3FF4-4673-A0E5-03B9FD8E9892","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"5716bd614d0a389f769b01822451f8ee8d33b4ba","datavalue":{"value":"model-free methods","type":"string"},"datatype":"string"},"type":"statement","id":"Q5955768$5EDD02B6-21DD-4721-B0A5-CF1FF84DE26A","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":"Q5955768$03A76B93-E734-4575-961C-B9D0EE493A33","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"c3f98460b384828c8bf83357f491805285c2caa4","datavalue":{"value":{"entity-type":"item","numeric-id":4074727,"id":"Q4074727"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$2598DF94-0B0A-4C8D-96B8-252EE5A12D0A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"98844730d9c1688322efd9feb9c275dd6cdbf9da","datavalue":{"value":{"entity-type":"item","numeric-id":5186740,"id":"Q5186740"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$B3BE402E-F16B-4BB2-9EB9-93BAB3469240","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"70c51dcf350be2e2bfe199214bbe4e8e45d955f1","datavalue":{"value":{"entity-type":"item","numeric-id":1154810,"id":"Q1154810"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$3A737D4B-F43D-457B-A7C9-11810B10CB0F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"a33baa9f598c25028c954b3e94d0bf34fc147383","datavalue":{"value":{"entity-type":"item","numeric-id":1149264,"id":"Q1149264"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$58A40523-D655-4212-926C-6825D062B75A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"a308e30505dd380998190c7f81f45679fe7a55a5","datavalue":{"value":{"entity-type":"item","numeric-id":3292915,"id":"Q3292915"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$333AF595-E4D0-4041-A12C-C01DCFB7FBA3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d06e8bb442a11e5a3e41e506dc3cf3e777c626a3","datavalue":{"value":{"entity-type":"item","numeric-id":3955990,"id":"Q3955990"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$52B37769-EA23-4CB9-B99C-266877088537","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"3c9d278f5223b5af6a8a4aceaba222884fd9a696","datavalue":{"value":{"entity-type":"item","numeric-id":4001523,"id":"Q4001523"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$6A2D6572-87A8-4FDC-B79F-425E5A727D12","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"5a49c9c35a3845bf025722ecb9dea8f0937606c9","datavalue":{"value":{"entity-type":"item","numeric-id":4013741,"id":"Q4013741"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$A0D28834-5672-4543-8F41-F9DF1D886A20","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"b5e962078ce73e91a0af0844091c4c5e70af651e","datavalue":{"value":{"entity-type":"item","numeric-id":2639648,"id":"Q2639648"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$1ADF6305-E211-4492-9C81-BEED844F2933","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"6b1b06b57fe9d47a111d5fa6cca00f392a2b3ca1","datavalue":{"value":{"entity-type":"item","numeric-id":3688190,"id":"Q3688190"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$2181A0C1-39EB-48E7-8CD4-50B9184C0A49","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"f69cd5c0423133b18fe1911a4ca34fd3826b06a4","datavalue":{"value":{"entity-type":"item","numeric-id":5615053,"id":"Q5615053"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$AB33A0CD-3332-44E5-834F-7A4A7B4D3886","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"481cc18be6fb59115f57e85e36f744a549c960d1","datavalue":{"value":{"entity-type":"item","numeric-id":3683893,"id":"Q3683893"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$B564D722-4D68-44FF-ABBE-5326CE589CFF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"abf84cf95adcd15c6620e46debc5526d545ffe82","datavalue":{"value":{"entity-type":"item","numeric-id":1812933,"id":"Q1812933"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$C09E8881-2983-4D93-8CD7-B1E81EFE5325","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"bf9b1ff0277f4634918819d48177b043fe71600c","datavalue":{"value":{"entity-type":"item","numeric-id":1812929,"id":"Q1812929"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$67A7A338-E67E-4CEA-A31F-72530CF539B6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"52ff99291fc23db333da452abed8dce9cbb5fdc5","datavalue":{"value":{"entity-type":"item","numeric-id":1812931,"id":"Q1812931"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$8E9D09AB-168A-4294-A56D-A39B9587535B","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"b6caf6f592cda804f308cce8758ed604562ef633","datavalue":{"value":{"entity-type":"item","numeric-id":673759,"id":"Q673759"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$2C810840-F27E-4724-98AC-3ED8859AFD14","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"125865d688d43e7f0119a3476237afb2b0154934","datavalue":{"value":{"entity-type":"item","numeric-id":301778,"id":"Q301778"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5955768$44A3E330-A45C-4E28-BEAC-F3B854BA2CBC","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"532a87b322abfc3b4ccd493eb3d2fbbb9a0a339e","datavalue":{"value":{"entity-type":"item","numeric-id":2901057,"id":"Q2901057"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"1095fae7eda15276e49c265d2e651d1bbd8180c2","datavalue":{"value":{"amount":"+0.8346832990646362","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5955768$E78C9356-BA0D-4977-830B-0AD8E6A69CFE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"fa2027187559efd900f7298e9e357895cbfcb45b","datavalue":{"value":{"entity-type":"item","numeric-id":1600659,"id":"Q1600659"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"6aef25a22ee3c4fed617863bbac2583c5e21d18b","datavalue":{"value":{"amount":"+0.8100545406341553","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":"Q5955768$3AB248BF-FAF1-4709-8BC3-045B186AB94A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"493b359fe2fcba9f4f226125668aad907932f2a8","datavalue":{"value":{"entity-type":"item","numeric-id":5168383,"id":"Q5168383"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"6aef25a22ee3c4fed617863bbac2583c5e21d18b","datavalue":{"value":{"amount":"+0.8100545406341553","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":"Q5955768$7B59937F-7989-40A4-8ADD-4C4835D03611","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"d70c5a169d0e24f15ce9ab85a2a68e2b640047fb","datavalue":{"value":{"entity-type":"item","numeric-id":1812928,"id":"Q1812928"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"baecea3d0cad54e55065659455905e11797ef259","datavalue":{"value":{"amount":"+0.7904328107833862","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":"Q5955768$1A1BDD61-8C8C-420C-8B77-F584A1A43FA7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"b89ef273502c3ba4bf4da5f411c900d32beea5f8","datavalue":{"value":{"entity-type":"item","numeric-id":4413265,"id":"Q4413265"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"7947aeed64d3ea61e465e075f30d6a899c990e8b","datavalue":{"value":{"amount":"+0.7764463424682617","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":"Q5955768$9261E40E-23E1-4EED-B1F6-613DD26CE7F7","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Publication:5955768","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Publication:5955768"}}}}}