{"entities":{"Q6893677":{"pageid":20858590,"ns":120,"title":"Item:Q6893677","lastrevid":75451498,"modified":"2026-04-19T03:17:41Z","type":"item","id":"Q6893677","labels":{"en":{"language":"en","value":"Stochastic first-order methods for average-reward Markov decision processes"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 8128106"}},"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":"Q6893677$C659548C-94AD-41BB-9263-3C16E6EE9253","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"8901a6ae18f11ce27d0bfcdbbfec3d58806b24ff","datavalue":{"value":{"text":"Stochastic first-order methods for average-reward Markov decision processes","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6893677$F99FB8F7-AEFC-4224-953F-40F934700EAA","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"c7fde7dbed12ba85f97801ff0621fe404455deb3","datavalue":{"value":"10.1287/MOOR.2022.0241","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$6711A522-5D2C-4012-923D-06CA361805AF","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"972748756ab6db0294ed4fa1288fcc92ece9159a","datavalue":{"value":{"entity-type":"item","numeric-id":5081105,"id":"Q5081105"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6893677$B7447913-42B6-42C0-8B38-EF89761A4BC6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"276db839a6a8a3697270e3b4b72fe4ae04928330","datavalue":{"value":{"entity-type":"item","numeric-id":6893676,"id":"Q6893676"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6893677$62837388-AA0C-44D3-B089-CF33771900A6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"98b81c1c93f265b5da2468024dc69df10945c79f","datavalue":{"value":{"entity-type":"item","numeric-id":245488,"id":"Q245488"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6893677$0BF8954F-B4AA-4009-89DC-58BE1835CAC5","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"cccce4a4205b51ff587d222bc7a07ed4bfa86d8f","datavalue":{"value":{"entity-type":"item","numeric-id":103831,"id":"Q103831"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6893677$D48E174C-BD5F-4870-8CA9-933BEE2F29BF","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"46b64429f4db778a47f40be8c6fa42e140125f60","datavalue":{"value":{"time":"+2025-11-26T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6893677$520773BF-115D-45C0-B52B-22E873C0C503","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"69417b84cc431ede4e5ec12a55be58b45cd19ec0","datavalue":{"value":"60J22","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$DFC56EAA-66C0-4E19-9090-20E9C967F563","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"1cdf15533e26fc0c4c2e22d28e655c364dfe77a6","datavalue":{"value":"60J10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$D6F85DFE-8046-45F2-AC61-48610B17153C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$906BB988-793A-4EBA-B526-FDB4417C4AAD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"dade3bc82a2f7e555fdd92f6a7aa24c002fcafaf","datavalue":{"value":"90C15","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$A6119BEB-E607-475F-A666-D507DACEA8F8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"52de7d4bf5a27d5ad252804eec58396bb3e40c44","datavalue":{"value":"90C30","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$DA2644F9-AD02-4529-BCD0-094E3C8119B7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"b23b4581d19061667c697da14a890aa055e6f323","datavalue":{"value":"65C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$26D0195E-B980-4662-9CAB-CC56466873F9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"fdd9498216d1fd2eff80e5a7d18782b649eb7b2f","datavalue":{"value":"68Q25","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$C1F5C73C-56AE-4FC5-80FA-2369101E40DE","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"f517708d962e561876ddda346b64d34701f82499","datavalue":{"value":"8128106","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6893677$AC528C34-F05F-466E-8FF1-2D2A85485DF1","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fbd1f99995fb6a13da62a377ba6327166316e976","datavalue":{"value":"Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$0557097B-8B67-41B9-8970-BC1FDE197134","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ae9ac33fbe281c7bf8565fa2c577496b9b65917c","datavalue":{"value":"average reward","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$F49B6A09-4688-4081-860E-81C6BA79AE05","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b746b53a2f361e140065f7f40c009d3cc80e61fe","datavalue":{"value":"policy evaluation","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$1C8D1735-42F7-45F0-9BA1-66968DEF1022","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"586d8ae342cc91fbbe50b01c60efed8832b560bb","datavalue":{"value":"temporal difference","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$CAD5336F-2B73-445D-A806-A1AEBE39A1AE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"0ce8083ebb2bd4c6dd9f735e5796464ac4303167","datavalue":{"value":"policy optimization","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$CE40767F-398E-41D1-BC57-58F22D1928A9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fe124efd6192c449721b5d003e73cb625b95c849","datavalue":{"value":"first-order method","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$3D845054-61CE-4224-9B7E-B71358B9963E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"29ffc52c901d6c6ab06fbba6b0951d44bbf50c15","datavalue":{"value":"policy mirror descent","type":"string"},"datatype":"string"},"type":"statement","id":"Q6893677$1A679EBE-9E52-4C24-A026-C33E21284A13","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6893677$E30D2ABA-5DCA-47B8-8293-B1514E3AD33F","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Stochastic first-order methods for average-reward Markov decision processes","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Stochastic_first-order_methods_for_average-reward_Markov_decision_processes"}}}}}