{"entities":{"Q4969098":{"pageid":6998677,"ns":120,"title":"Item:Q4969098","lastrevid":58369578,"modified":"2026-04-04T22:21:50Z","type":"item","id":"Q4969098","labels":{"en":{"language":"en","value":"Expected policy gradients for reinforcement learning"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7255083"}},"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":"Q4969098$7B4FFA47-3FA2-487D-8363-5280E27D5A45","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"9584c06d36f69c606955a0312edcff920400ddbb","datavalue":{"value":"1498.68229","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q4969098$7FE50EDC-B070-4659-8C81-6083E9BE4521","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"f28ff5121e20cd1292c83f233b945e4373431ec1","datavalue":{"value":{"entity-type":"item","numeric-id":4969097,"id":"Q4969097"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$9FDA1BEF-AB1A-4604-A66D-9D7AF18F1904","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"8d0290f3d03ddfc90c0c5087d1ef2609ca6eb874","datavalue":{"value":{"entity-type":"item","numeric-id":980850,"id":"Q980850"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$ED1B40AB-4E51-4AB9-8C50-3C54B8E225DE","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"98145858bd8b0e44fddc1472bb2c2b5069f5382c","datavalue":{"value":{"time":"+2020-10-05T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q4969098$B93B7B2F-A060-482E-A01B-3B2FD8072AFB","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"f3a3765cc7943ec4624c90029b82ed2c9e6a85a6","datavalue":{"value":"https://arxiv.org/abs/1801.03326","type":"string"},"datatype":"url"},"type":"statement","id":"Q4969098$9AC3D436-55DE-42AE-9EBE-3573D0E5DF97","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P205","hash":"02933910fc7d3f69b33aa313ab1f0ec4f6f9e2f7","datavalue":{"value":"https://jmlr.csail.mit.edu/papers/v21/18-012.html","type":"string"},"datatype":"url"},"type":"statement","id":"Q4969098$67384537-59AB-4BBA-AC8F-23C62B6B6454","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q4969098$80BC39BD-F519-4862-AE66-6EF4A205B3BC","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"5d625d780bfa809c5db39c69099009106c2aeb44","datavalue":{"value":"62M05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q4969098$036B9850-A215-46DC-9A26-5E8F1F74C0CA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q4969098$6A1E83F1-D139-44DB-AEA8-57708E722C64","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"9a7f73384af56f0f2d5b4476f98754f5bbdb67a0","datavalue":{"value":"7255083","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q4969098$BCCD8DFF-6AA1-46F1-B8BF-959C3B54205E","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"e62100112f5cfbfcadab65b58944e034786dfe24","datavalue":{"value":"policy gradients","type":"string"},"datatype":"string"},"type":"statement","id":"Q4969098$B0B480BC-C22E-48E9-9736-5E4A21A5BAED","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"bad89e909476aa8677f8649838f1a557dc69e022","datavalue":{"value":"exploration","type":"string"},"datatype":"string"},"type":"statement","id":"Q4969098$09E26EF5-CAEB-4706-BCC2-D05A929EE70E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b5f0ebb933ed1948974d17e0b6801d0f39e7f4bd","datavalue":{"value":"bounded actions","type":"string"},"datatype":"string"},"type":"statement","id":"Q4969098$2353A0A1-1A01-408D-91CD-A15594F01180","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q4969098$8C337328-6D47-43EA-B674-53BACEFAF993","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"107db0753fad68217a5c18726848e1cf557718d3","datavalue":{"value":"Markov decision process (MDP)","type":"string"},"datatype":"string"},"type":"statement","id":"Q4969098$0C1D8720-92F9-4941-A68C-A940809C989A","rank":"normal"}],"P1463":[{"mainsnak":{"snaktype":"value","property":"P1463","hash":"27d0ba0f2385e1f67c7a3b66f367fed0cf34c380","datavalue":{"value":{"entity-type":"item","numeric-id":27063,"id":"Q27063"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$343E0EF5-4751-4FAA-8188-4A588501073C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1463","hash":"a28c49518b2391a3c9e2da3891679e04c0308e5d","datavalue":{"value":{"entity-type":"item","numeric-id":32752,"id":"Q32752"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$02F95754-C390-4118-B4AE-7860AAB63FEF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1463","hash":"38fe1944878b0e3ec6c02df226eda459a0e11b64","datavalue":{"value":{"entity-type":"item","numeric-id":33999,"id":"Q33999"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$E9A7CC1F-EB42-47A5-9561-C18894847E41","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1463","hash":"30bf75efb36ce548a631ba3177096a709329cc05","datavalue":{"value":{"entity-type":"item","numeric-id":34000,"id":"Q34000"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$7C858AE8-8CD1-4837-8EC6-EBCE227078DF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1463","hash":"69f9c04383cda1c09a88d33797aa54a343a5df19","datavalue":{"value":{"entity-type":"item","numeric-id":38932,"id":"Q38932"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$7D8269AA-45AB-4F0B-A496-A73B92B7319A","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$B2ABE348-70D6-45B9-9826-6280A49D7A76","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"de8dbbced31b8a5dcf0f3766a133e04f775a95f2","datavalue":{"value":{"entity-type":"item","numeric-id":4558153,"id":"Q4558153"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$847BBCAC-E304-43E7-8CD5-B2BF8CE177A5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"ed095db7727f2861ac91aa6b587f5e77f36ae0b4","datavalue":{"value":{"entity-type":"item","numeric-id":1049136,"id":"Q1049136"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$B82A90E5-3E0B-4D88-8740-29E20BC40F94","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"1ba8a58f87fe8be7c23d2712989942d783ae8893","datavalue":{"value":{"entity-type":"item","numeric-id":4188569,"id":"Q4188569"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$BAD9E995-9D42-4B0B-8132-97002961CE69","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"1c8b161d1542872b8fd2ce4acb35d5f725562893","datavalue":{"value":{"entity-type":"item","numeric-id":4821821,"id":"Q4821821"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$9F4E5C03-B590-4D30-936F-387024F803F4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"5f83f58b20f2666d0fc775b488900fec53144b31","datavalue":{"value":{"entity-type":"item","numeric-id":2953657,"id":"Q2953657"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$BED6A9A1-B26D-4C30-8DF7-234494BB99D6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8230e3b10153745792ae9d858efd5c4d73e9a1a5","datavalue":{"value":{"entity-type":"item","numeric-id":2810874,"id":"Q2810874"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$995722CE-0956-4BF6-AA26-ECA042EB6FB4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"a035d51a544715d86645afd1d3e45a6405b3d11f","datavalue":{"value":{"entity-type":"item","numeric-id":4826001,"id":"Q4826001"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$BA3AC037-C529-4088-A93D-51B96608ED4C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"6c9f07ae37efbba5d31990542c72042ab7fe4d12","datavalue":{"value":{"entity-type":"item","numeric-id":2829188,"id":"Q2829188"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$946E0EDD-685E-4555-A133-0D293E0F1CF7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"cff77bc05f5f323bf565efc5e00737ddf97726e8","datavalue":{"value":{"entity-type":"item","numeric-id":747252,"id":"Q747252"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$ED58F15F-1996-4202-8ACF-4995D67B1597","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"42899df5b07f98507ca87f01b80430013eb00ad3","datavalue":{"value":{"entity-type":"item","numeric-id":4315289,"id":"Q4315289"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$8BAFD895-9914-416B-8F3A-B27DDA277D98","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"09de85cb40407078891b3ac12bb36d9f6851a7bb","datavalue":{"value":{"entity-type":"item","numeric-id":4573480,"id":"Q4573480"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$9A119F41-64A7-48D3-878C-7D2CE496B801","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"6d3bd02791f3fd6f2c39b3ae9244b7d656a93c72","datavalue":{"value":{"entity-type":"item","numeric-id":4626283,"id":"Q4626283"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q4969098$DD975EC7-0686-4B51-A506-0525A52B53E7","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"2019e98818d30fa59546a65dfe28c08b7ce70b06","datavalue":{"value":{"entity-type":"item","numeric-id":5378202,"id":"Q5378202"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"a9ff5a910acfbce7a79234d5c9357025505434cf","datavalue":{"value":{"amount":"+0.7708720564842224","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":"Q4969098$1C82325A-9ADD-4DB7-88E4-C9F4E60C52CA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"479c5a2370a1814ae22515460a6f4221f7066823","datavalue":{"value":{"entity-type":"item","numeric-id":448295,"id":"Q448295"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"33a0b51e4843960639ed2942c2d247bf54c18339","datavalue":{"value":{"amount":"+0.7626625895500183","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q4969098$C666B4E3-E966-453B-B471-91B328FF92BE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"d76723d9c797f632b12d82c4181e4ba391e35ea8","datavalue":{"value":{"entity-type":"item","numeric-id":2810874,"id":"Q2810874"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"b48d649efb7b980d92ff8b38b20f46f9813a7e7d","datavalue":{"value":{"amount":"+0.753645122051239","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":"Q4969098$224AEE89-68B0-4E55-8EBF-668409B9BD16","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"adfc7d8d26ff988e3fab089d5d325f562f8bffd0","datavalue":{"value":{"entity-type":"item","numeric-id":3093369,"id":"Q3093369"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"437bc93f27d36a111bc5161797aabd8c9bc445ad","datavalue":{"value":{"amount":"+0.7460470199584961","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q4969098$BEF5D354-C159-40E0-9713-A12924B967EE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"2ffdc8bc4f6162c8d2bcb48ec44ee7431be8ec9d","datavalue":{"value":{"entity-type":"item","numeric-id":3093234,"id":"Q3093234"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"e4ed31c4396037b80cb27d69e8f49f3d632c1f60","datavalue":{"value":{"amount":"+0.7456057071685791","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":"Q4969098$F8C020D2-9AE8-494E-8369-89266A7B8ABF","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Publication:4969098","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Publication:4969098"}}}}}