{"entities":{"Q2953657":{"pageid":2964377,"ns":120,"title":"Item:Q2953657","lastrevid":85336691,"modified":"2026-06-03T07:06:49Z","type":"item","id":"Q2953657","labels":{"en":{"language":"en","value":"Approximate Newton methods for policy search in Markov decision processes"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 6670752"}},"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":"Q2953657$5F00319D-183C-4140-93E1-90B079EC6A07","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"01feec4a3e4593bf9d79ec2fc83a28162c184e1a","datavalue":{"value":"1404.68102","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953657$98191317-3B25-4328-AB73-80280D1AC1D2","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"c42d58d3be372fa589ac419e7ec7c6dd33e618e4","datavalue":{"value":{"entity-type":"item","numeric-id":2953656,"id":"Q2953656"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2953657$648E1B10-B81E-47D3-9CF4-7530CDA188CD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"5da2b275609b2934a410f877d7cdb90d68ae615a","datavalue":{"value":{"entity-type":"item","numeric-id":1939258,"id":"Q1939258"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2953657$627C92C9-94C0-4BAC-A337-939078EA1C5E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"5483f0d0d50a9fcb35807a7c4fd2be96d4064514","datavalue":{"value":{"entity-type":"item","numeric-id":232855,"id":"Q232855"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2953657$C02E91A0-E7A5-4F96-AC0D-C2F304885588","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"760e9b62711d69fa60d91085ddfcfbb47e8478ef","datavalue":{"value":{"time":"+2017-01-05T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q2953657$F8BF0293-0CC2-4242-B69C-8F00B9B900A3","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"e2a36b8e8b4f6e229a20e0cb5b2d759df855b44a","datavalue":{"value":"https://arxiv.org/abs/1507.08271","type":"string"},"datatype":"url"},"type":"statement","id":"Q2953657$0DA5304C-9E45-426A-8EED-F21211BE8B64","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P205","hash":"189aa8766bd901676f8794d0036d4dd25813f14c","datavalue":{"value":"http://jmlr.csail.mit.edu/papers/v17/15-414.html","type":"string"},"datatype":"url"},"type":"statement","id":"Q2953657$8B881E62-E976-4918-A171-08EE30E07B96","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953657$6B548193-CA51-4505-8EF4-90A84435E4D2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"e57e2977a9ed0e05339dd5f1673c9f0c9ab91235","datavalue":{"value":"65H10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953657$DD8EF222-26DC-4E2E-957D-72DE98B6CF47","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953657$34833D6E-688D-40D4-81DA-4254CCBFE157","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"519acc9341921c432177e0b1083b7eeaa0bbf985","datavalue":{"value":"6670752","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953657$1CD6D6A2-308C-4102-8E8C-66DCF257DDC7","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fbd1f99995fb6a13da62a377ba6327166316e976","datavalue":{"value":"Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953657$5F15CDBC-E898-494F-B122-B8533DF5041C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953657$9A7B098C-B201-400D-BD3C-87A93F68F645","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"19fa163078e6aba4ca84a0cee85767b7a972a3eb","datavalue":{"value":"Newton method","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953657$A73B5E8F-573F-4C26-9868-E1B9AE8CB335","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"552a0fbf62290d4861ca327f137adb07a4cc5e11","datavalue":{"value":"function approximation","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953657$BC38B7F4-6FAE-431F-8CA3-4D83B4F66BC7","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":"Q2953657$71438698-B23C-4211-A173-607A20EDAB72","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"b7281879659838ec849586d1d9cea44454cd0ee3","datavalue":{"value":{"entity-type":"item","numeric-id":6074547,"id":"Q6074547"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"514c50224130c818338eaff3643a0d8cc50af5e1","datavalue":{"value":{"amount":"+0.835472047328949","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":"Q2953657$9B4CFC05-A349-4E59-B16B-A74880E0C091","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"c194a39612230702fb5e4eac2422a4273f23773e","datavalue":{"value":{"entity-type":"item","numeric-id":1870312,"id":"Q1870312"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"3afc521be6f38a3d85782c9d002f518ae49e47ab","datavalue":{"value":{"amount":"+0.7687663435935974","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":"Q2953657$7FCE0CE0-32B7-47D5-BCA6-2FC90F9D5EE0","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":"ecc975ab1ef111dcba58c7d12c1c16455b3749a2","datavalue":{"value":{"amount":"+0.7396215796470642","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":"Q2953657$002AD61A-5D1C-4AA6-B213-F958C52AF487","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"592c932bf50b30de44dc0103fafadeac7eff5da2","datavalue":{"value":{"entity-type":"item","numeric-id":3415884,"id":"Q3415884"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"7945ffaae34252fed590b96fa77ae27c1efa0009","datavalue":{"value":{"amount":"+0.7325055003166199","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2953657$E46DA2CF-86A2-4866-8FE9-5DBB2522D27B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"8c1ef27ae72a3dcb195ebba4770c3dcd773ca879","datavalue":{"value":{"entity-type":"item","numeric-id":2670744,"id":"Q2670744"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"68e31e7418e707691bac06682cb35f4938cfb7a9","datavalue":{"value":{"amount":"+0.7163335680961609","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":"Q2953657$4812E8B3-BC5F-4AF2-ABF6-7754A1E634AE","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Approximate Newton methods for policy search in Markov decision processes","badges":[]}}}}}