{"entities":{"Q2810885":{"pageid":2821623,"ns":120,"title":"Item:Q2810885","lastrevid":58023468,"modified":"2026-04-03T12:06:27Z","type":"item","id":"Q2810885","labels":{"en":{"language":"en","value":"An emphatic approach to the problem of off-policy temporal-difference learning"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 6589487"}},"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":"Q2810885$5F844372-9AFC-4E8B-A294-5124E94C5849","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"e61894c6a76b023470f5f3af96bfda28dee3b707","datavalue":{"value":"1360.68712","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2810885$1EAFD2A0-6649-4D3B-8530-6A3FAD0E49C0","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"1d0463f1e7d2643065a0fb126a3a03aa8a0fd3ce","datavalue":{"value":{"entity-type":"item","numeric-id":1049133,"id":"Q1049133"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2810885$6954FBBB-5135-4625-BC1A-42AC2A8ED784","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"2ca949b0a8509885c0bdaa48bf07bed6efcbbe8e","datavalue":{"value":{"entity-type":"item","numeric-id":2810883,"id":"Q2810883"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2810885$9F728DA1-E287-47CA-9CEF-143A3EEE0D32","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"1c5d7a6e6cf1ea5d86a41baf62581b9247030527","datavalue":{"value":{"entity-type":"item","numeric-id":2810884,"id":"Q2810884"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2810885$512DDC22-702B-44A0-86AF-EFBED7FEF7A7","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"d066e43a0d378deda532184f86b234184fe2275a","datavalue":{"value":{"time":"+2016-06-06T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q2810885$04CCD6CE-BD3A-4310-8F5A-91137A615240","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"b736406b31e07eb4b7f58879a7ff622ebfa07952","datavalue":{"value":"https://arxiv.org/abs/1503.04269","type":"string"},"datatype":"url"},"type":"statement","id":"Q2810885$FA7FC958-B979-4A4F-BA9C-A96836B7C9F3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P205","hash":"de830a6da2099387bf65681d77a51251664130b6","datavalue":{"value":"http://jmlr.csail.mit.edu/papers/v17/14-488.html","type":"string"},"datatype":"url"},"type":"statement","id":"Q2810885$0AE3DBBE-9E1A-40F7-8108-EEAF2A28F997","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2810885$03784CAD-1278-4E59-A69C-6345F7C3AF05","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"8cc3a43dfd4d746f7f2d259ed4984f5d4715e80e","datavalue":{"value":"6589487","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2810885$5CFA3477-AB6F-4B94-8337-5EC62105BC8C","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"6af621a71a9b2582910438f628068ab5f6f5f22d","datavalue":{"value":"temporal-difference learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q2810885$6F9F6924-6B6A-4A86-846E-C91CDC2D9AF1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b20323195e76e4f85c038d0f8828588ec6fa67ac","datavalue":{"value":"off-policy learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q2810885$357C3C9A-51A1-4DD5-87CC-321523F9D048","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"552a0fbf62290d4861ca327f137adb07a4cc5e11","datavalue":{"value":"function approximation","type":"string"},"datatype":"string"},"type":"statement","id":"Q2810885$B8896B85-923B-4586-B348-57BC04667C26","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"34b44e7b40021effdee26093512bde7058814281","datavalue":{"value":"stability","type":"string"},"datatype":"string"},"type":"statement","id":"Q2810885$A476CE8D-3577-49F2-B972-D31BC2D16117","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"03ee0109af41ad406ecd743518061baaa9e5e3ff","datavalue":{"value":"convergence","type":"string"},"datatype":"string"},"type":"statement","id":"Q2810885$C251D3E0-35A6-4553-9FE8-6A5110738689","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":"Q2810885$C4A38AD8-C64B-45E8-BD1C-F7018BCA4E85","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"b29dc20b2cd162f784399669fdb6bed1dad6d522","datavalue":{"value":{"text":"An emphatic approach to the problem of off-policy temporal-difference learning","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q2810885$AFA4C054-3B9A-4A79-AC6E-69535C13B52A","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"05810dfd27f2b8a246f7d0a5b34fbcc72e448b7a","datavalue":{"value":{"entity-type":"item","numeric-id":6582882,"id":"Q6582882"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2810885$AABAFD0E-6A1A-4EBC-8516-A2AC1A589F90","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"37f6d620a64aaa562cdc98e03a2f663b83a2d5e0","datavalue":{"value":{"entity-type":"item","numeric-id":2953645,"id":"Q2953645"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"e4ef98c86a6da8bb459c4a2be5bd66151dcf2000","datavalue":{"value":{"amount":"+0.7877683043479919","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":"Q2810885$1E39F421-F9C8-4544-9EE9-C4EC5275613F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"01a45f21cabe21478c08a317cbb160c68b74a947","datavalue":{"value":{"entity-type":"item","numeric-id":2831390,"id":"Q2831390"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"1c89201230431a96fc3e5160389c2237978d9f3d","datavalue":{"value":{"amount":"+0.7836378812789917","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2810885$FF8A26AA-52C0-4143-8A3B-2E0851791917","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"faf59e9a2a542e5b797567ea67e1e81fffb07de5","datavalue":{"value":{"entity-type":"item","numeric-id":5003727,"id":"Q5003727"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"bcfedeab21668f04cb24684ff4f80bbc5a8de501","datavalue":{"value":{"amount":"+0.7710335850715637","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":"Q2810885$96A4F807-DB1A-43D7-A9F2-858159326626","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Publication:2810885","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Publication:2810885"}}}}}