{"entities":{"Q6663113":{"pageid":14274270,"ns":120,"title":"Item:Q6663113","lastrevid":95735294,"modified":"2026-06-05T09:40:33Z","type":"item","id":"Q6663113","labels":{"en":{"language":"en","value":"Policy mirror descent inherently explores action space"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7966996"}},"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":"Q6663113$79B4C3C0-6354-4318-9513-30FBC9E81820","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"bae2b94bb8c1c21cd011650ee0379973332e6acf","datavalue":{"value":{"text":"Policy mirror descent inherently explores action space","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q6663113$1F7DC4F3-2B34-4878-8DC2-D115040E5289","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"40335ca4f77c036f9786129f11924c5ef45c2393","datavalue":{"value":{"entity-type":"item","numeric-id":1748861,"id":"Q1748861"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$5994BA45-F70A-4378-9F2A-CA8A5F6C3C3F","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":"Q6663113$1F46FAAA-22A2-4D95-A52F-2019C30B9309","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"695f2c366d4da65eefbadd7f5b4277ec35b5cedc","datavalue":{"value":{"entity-type":"item","numeric-id":60872,"id":"Q60872"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$C21BFF18-0FB7-4546-A4F9-E56CCB6E00CC","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"b939f7d6bb04335f584ac4f12e27b7d35776737c","datavalue":{"value":{"time":"+2025-01-14T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q6663113$66785EB3-6267-44CE-9B83-2DA2C27AB68B","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"377d3ab03372cff12915e0de0374438ff70c3716","datavalue":{"value":"90C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6663113$0AC4ED14-F21F-4B09-89B1-1DBBABA576E6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"dade3bc82a2f7e555fdd92f6a7aa24c002fcafaf","datavalue":{"value":"90C15","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6663113$1D617D52-8D2D-472E-B9C9-9AF59A7559D8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"ed10a41ec587cb61dc683f25ef4b3e827c7fee2f","datavalue":{"value":"90C26","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6663113$453DC2FB-56AD-46E7-AEFE-9784F6C4A1D1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"fdd9498216d1fd2eff80e5a7d18782b649eb7b2f","datavalue":{"value":"68Q25","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6663113$2BCB98CA-7D9E-47FF-BC48-061E19CB7D72","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"fd1bdf532ac9a0ca7f8c03e1218adff1842bb286","datavalue":{"value":"7966996","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6663113$E2455443-A332-4958-B63A-AC08A2165044","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"a8cfb635100bcc8a85463e6beac1ce534f15033d","datavalue":{"value":"Markov decision process","type":"string"},"datatype":"string"},"type":"statement","id":"Q6663113$CCD7D612-893C-4465-87F4-B804AF57DD59","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"cbb231d289f74f1e03fd2bd1c238b0fedc7fdd73","datavalue":{"value":"stochastic policy gradient","type":"string"},"datatype":"string"},"type":"statement","id":"Q6663113$B65C42A1-BD36-42FD-B995-2E847FC88CBD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"bad89e909476aa8677f8649838f1a557dc69e022","datavalue":{"value":"exploration","type":"string"},"datatype":"string"},"type":"statement","id":"Q6663113$5FC3082C-636D-4471-9AF7-DDD1E398CCE2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab36e1f028d08bef5cda231bb7c5ad685fe0a94a","datavalue":{"value":"mirror descent","type":"string"},"datatype":"string"},"type":"statement","id":"Q6663113$0F2B2397-F231-417B-A185-93AC091FB9CF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"069723b5518c531a3e45ceb3a7ca0ae760d0fab9","datavalue":{"value":"sample complexity","type":"string"},"datatype":"string"},"type":"statement","id":"Q6663113$3B4B51C2-F470-48D6-9738-33D90A793A1A","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":"Q6663113$48EEFD44-8A28-442A-A4E5-DE961BFC0AE1","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"f5ab497481664a4a07920e158c21460796b4eabb","datavalue":{"value":{"entity-type":"item","numeric-id":4785631,"id":"Q4785631"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$D973C850-5224-4B3D-B9D2-4AC5A76A61D7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d61c33b5fe7a64dd8dfc393ef274dfc6f9b47cff","datavalue":{"value":{"entity-type":"item","numeric-id":5106383,"id":"Q5106383"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$B0729F4B-7691-4759-9CAB-E5A83112A25E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8f807985560178835d27958ada0cfa42962d4181","datavalue":{"value":{"entity-type":"item","numeric-id":6080164,"id":"Q6080164"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$0D3E04F3-AA80-4AEB-A7A7-B509F8049BC7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"b9c633876d672129d6a3e4e8a9ce4ff826b09852","datavalue":{"value":{"entity-type":"item","numeric-id":5081106,"id":"Q5081106"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$5F10DAB4-42C6-437F-9A29-9A99FCCDFFDC","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d0b556d51b5e676c221d0327f63920155af2c236","datavalue":{"value":{"entity-type":"item","numeric-id":1060517,"id":"Q1060517"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$C5398B62-9D62-48D4-AAB9-12A4E723389F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"f72d10be9a364751622fb84a77b9320272cadd77","datavalue":{"value":{"entity-type":"item","numeric-id":2687069,"id":"Q2687069"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$D076DC14-5C10-4FD4-976A-1A9BCC9D03D8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8493a5a62024019346aaeba9ffda17b4211df2f9","datavalue":{"value":{"entity-type":"item","numeric-id":6093281,"id":"Q6093281"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$B5DA0CC8-FF1B-4426-8228-721CA7E64827","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"912720a13d28229f567e09e063b6af9d00dd4cf5","datavalue":{"value":{"entity-type":"item","numeric-id":4595047,"id":"Q4595047"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$1101A934-70FF-4E88-B84A-31D559153618","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"a3d3a9a14f816b2ff88001fa69bd4ff11fb721e5","datavalue":{"value":{"entity-type":"item","numeric-id":6608040,"id":"Q6608040"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$B48D151D-1395-46C2-946C-4D089F031063","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"f28ea9b477f5f6808649aa2bd783f43fee052d24","datavalue":{"value":{"entity-type":"item","numeric-id":3648521,"id":"Q3648521"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$57B20119-6332-4949-9E9A-41A2A8D47553","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"e2329ac0e708e00741c5c4cdd66a1c4add2d4e0b","datavalue":{"value":{"entity-type":"item","numeric-id":3967358,"id":"Q3967358"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$B5A8340B-1AC7-4D62-85B8-0EF8563E3C89","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"1990c53957162605cc559d9c7c9c38af8fddbf7f","datavalue":{"value":{"entity-type":"item","numeric-id":5305630,"id":"Q5305630"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$10BEE668-DC97-4C18-8A4D-10C955621E6B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"47988575208536efb94ee3aaa852f1fdaa176918","datavalue":{"value":{"entity-type":"item","numeric-id":1911343,"id":"Q1911343"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$A7469CAF-E633-45F6-B4D5-743154C31A39","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"6ccf9f198f09e879b1c132198c6efd9c1cc91681","datavalue":{"value":{"entity-type":"item","numeric-id":1604814,"id":"Q1604814"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$CE619CA0-C16D-421D-AF23-E4FC1B6DD1EB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"7d80c5ede34ae24439acdfee3fa79e93e4cf038c","datavalue":{"value":{"entity-type":"item","numeric-id":6161312,"id":"Q6161312"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6663113$C8F9212D-9335-416C-BF5D-7E350DEFA094","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"5190e1818c24ad5c1227719ff538d80d2a370ae2","datavalue":{"value":"10.1137/23M1560215","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q6663113$6D14BA4F-0F0D-44CD-874D-99A479A32083","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Policy mirror descent inherently explores action space","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Policy_mirror_descent_inherently_explores_action_space"}}}}}