{"entities":{"Q7035349":{"pageid":21714978,"ns":120,"title":"Item:Q7035349","lastrevid":76832652,"modified":"2026-04-25T07:22:13Z","type":"item","id":"Q7035349","labels":{"en":{"language":"en","value":"Model-based reinforcement learning for offline zero-sum Markov games"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7976706"}},"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":"Q7035349$7E448683-F999-4492-A2F5-90C8BC23154D","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"672e19222a78423d5dc6c759d1ecce6c6b5a3dcb","datavalue":{"value":{"text":"Model-based reinforcement learning for offline zero-sum Markov games","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q7035349$981306EB-82FB-47CC-9B2B-584909725C3F","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"92dc242b30467c6c5321e2048f0505e31f65a4a0","datavalue":{"value":"10.1287/OPRE.2022.0342","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7035349$00EC928C-B1DA-405A-B895-3508ABB1B98D","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"975afb9bdcb6e81a40fc4e87034c8716942138b3","datavalue":{"value":{"entity-type":"item","numeric-id":1192931,"id":"Q1192931"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7035349$C49DDFE6-F023-4BCD-ACCD-D66BFB4D3A17","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"54fbaf898860f50347e6e0b6cafa9eb9dd5d48fc","datavalue":{"value":{"entity-type":"item","numeric-id":6039765,"id":"Q6039765"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7035349$615D2124-314E-4D4F-A7B9-1BD1073E3055","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"48290c7920ff811b5170aab683f2b46ca3bbad5d","datavalue":{"value":{"entity-type":"item","numeric-id":1688975,"id":"Q1688975"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7035349$3BB2628A-71E6-4CA8-8ECB-676562C182E3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"f62f8435cb2c61f1b1c15ed0a3f0f56cbe339c0e","datavalue":{"value":{"entity-type":"item","numeric-id":586406,"id":"Q586406"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7035349$1F000112-E1A2-41BA-AF6E-B38D9221548F","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"da22dd798edb52cb4cd38ece3d93e1b6b18670dd","datavalue":{"value":{"entity-type":"item","numeric-id":71781,"id":"Q71781"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7035349$B18CC446-678B-423E-8201-76EF193E7EC5","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"33da80bab28d97f78915cc0569c211fc5c6b5e0b","datavalue":{"value":{"time":"+2025-01-30T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7035349$20BF8C69-BF36-4104-A176-E69C7C45E1A4","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"8f34675a74b150d19473221b06b085ebc8156162","datavalue":{"value":"91A15","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7035349$63E1DCC3-F727-4260-8608-38695109FEC4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"8a7dd7003e1269b5b10ff3f935da8af9e44f172f","datavalue":{"value":"91A10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7035349$3988D411-C422-4E17-B65D-FBD499E5EA5F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"b98cb7058a1e8e644c33a49a426b651c0e594493","datavalue":{"value":"91A05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7035349$2798FCD4-1AF8-4D8E-A744-16E342435C51","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"cfe779e91fe9c53ee133568259955801965765ae","datavalue":{"value":"68T05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7035349$90D3F8E7-630E-4443-A2E4-CF0EAFC91B98","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"195900d15424cd54f9e48a106cd1f1d564661dd6","datavalue":{"value":"7976706","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7035349$9E773E94-B14D-4B2E-888D-052EFCC6586A","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"8db575e7387820f1f15beb002d9df69e55699ac8","datavalue":{"value":"zero-sum Markov games","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$E3C9B218-BB0B-445D-B113-428715679D85","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"53dde8b387b5cd23f4abb2e117e873f60004406d","datavalue":{"value":"Nash equilibrium","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$76FFAAEA-88C6-4B1F-A0A6-D4D1516605C6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"287964d7abd80b2ec176a2a38331b9b2febd6081","datavalue":{"value":"offline RL","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$61F3D8CB-647A-4989-B516-991ADB17199F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"a81d5b4c10262f188c233e9378cf1e38a4ab66b2","datavalue":{"value":"model-based approach","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$A994EC91-26D2-4EE9-A9EF-996D79C5A3C8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"8ca4a5c9411a63f4c43b2ded5deb08db9f9ea98f","datavalue":{"value":"unilateral coverage","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$558F086A-C22F-4663-B3D3-65CDA36011B2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"bbbb1ce9959993f12ceb93455a5dd72bc2b7dadd","datavalue":{"value":"curse of multiple agents","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$A508424D-D514-4922-96CD-6E0EB9EE4FB2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"cf4acd6ca460aafc004f305f56ec3144e660806f","datavalue":{"value":"minimax optimality","type":"string"},"datatype":"string"},"type":"statement","id":"Q7035349$FAE1BC33-ACD2-43F8-83A1-AFAE2A77D247","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":"Q7035349$7B3C0827-9673-4A67-B262-939CA2AE2FEC","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Model-based reinforcement learning for offline zero-sum Markov games","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Model-based_reinforcement_learning_for_offline_zero-sum_Markov_games"}}}}}