{"entities":{"Q2953645":{"pageid":2964365,"ns":120,"title":"Item:Q2953645","lastrevid":85168226,"modified":"2026-06-03T06:08:21Z","type":"item","id":"Q2953645","labels":{"en":{"language":"en","value":"Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 6670745"}},"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":"Q2953645$5040D3C3-80C4-4B92-876F-A8D81AB5939E","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"1309644937aa8315823845199c622a8494f4e4a5","datavalue":{"value":"1404.68124","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953645$41B102C7-E5D7-4E68-8177-1353CF00B837","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"419931659e530ab18949689112de8020c92dca8c","datavalue":{"value":{"entity-type":"item","numeric-id":378729,"id":"Q378729"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2953645$2DF93E63-EFA9-432B-8367-891EB770E609","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":"Q2953645$8C5830DB-78E9-4B27-A916-23E4F3CE0B98","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"74f80f0610b32a9a6dd0d2055bb8f1b30dc54ecf","datavalue":{"value":"https://arxiv.org/abs/1511.07471","type":"string"},"datatype":"url"},"type":"statement","id":"Q2953645$02A3CDF4-F54F-40B1-9AC0-9C9E14459523","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P205","hash":"56e778007d248a7ba27da7ff95b7d3d94d6ea2a1","datavalue":{"value":"http://jmlr.csail.mit.edu/papers/v17/16-242.html","type":"string"},"datatype":"url"},"type":"statement","id":"Q2953645$AED32842-1A45-4F5B-A035-12518694C74A","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953645$FB083287-7C31-4C71-B912-B9AE61E9B07B","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"728eb33dc16bd64751d617cf5af4a8b967dbfd18","datavalue":{"value":"6670745","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2953645$B343B9DC-0116-4B8B-88FC-BCEB1363D840","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fbd1f99995fb6a13da62a377ba6327166316e976","datavalue":{"value":"Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$02E1697A-9CED-43F4-8664-1CA062D673C0","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"c24907e29c5500b47e1335732316daec83c7635f","datavalue":{"value":"approximate policy evaluation","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$E9FEB96B-64E0-4CC5-92A3-A9709F3B746D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$6B58BE89-345B-4BCF-8B35-2F7F86DD7CEF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"6d9bee02ec40ce79e9d43098ba7e63e9c9417e52","datavalue":{"value":"temporal-difference methods","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$42B85BE8-5E6B-4DC6-8EE2-71F2594314CF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"6e3b9a2c122dd89be72ecbd4dd046019cd3c25be","datavalue":{"value":"importance sampling","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$7115566D-4CBA-4438-BA40-462C8FEF1B8F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"7c907e87ef34df25ac1895768a34fab33458ac88","datavalue":{"value":"stochastic approximation","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$4FF7D1E3-749E-4FE4-A242-8CA1068DA16C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"03ee0109af41ad406ecd743518061baaa9e5e3ff","datavalue":{"value":"convergence","type":"string"},"datatype":"string"},"type":"statement","id":"Q2953645$7271C424-CC0B-41F3-B65D-89C7C9A6478D","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":"Q2953645$5E8405A2-0D49-4657-AF1D-26E173592E8A","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"81a62751b92f8cd596b8a3c8d08fc874b299d030","datavalue":{"value":{"entity-type":"item","numeric-id":4910565,"id":"Q4910565"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"778c0e9a5b9817f58cc2f18960445f9267981551","datavalue":{"value":{"amount":"+0.7938724756240845","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":"Q2953645$44EB4C45-4AD1-4DE4-AF0A-6C15A8939AC4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"49c98e02597b76cfa1a5e2875bddc32216c3b39f","datavalue":{"value":{"entity-type":"item","numeric-id":1812934,"id":"Q1812934"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0badb5bbe40284462ab8860df8a0ddec1a66e423","datavalue":{"value":{"amount":"+0.7928056120872498","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":"Q2953645$9D18BC3B-0D11-4FBA-9555-11923BF97FF7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"95e0007aabc4de4b4fc8d4bc9dab1323b18debb5","datavalue":{"value":{"entity-type":"item","numeric-id":5219302,"id":"Q5219302"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"1c3de3ca66902900cda01c62e6ae3f4feb577d41","datavalue":{"value":{"amount":"+0.7897894978523254","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2953645$B8D8A987-79AA-4EAF-9BC1-337FC415AC67","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Weak_convergence_properties_of_constrained_emphatic_temporal-difference_learning_with_constant_and_slowly_diminishing_stepsize"}}}}}