{"entities":{"Q2129661":{"pageid":2140404,"ns":120,"title":"Item:Q2129661","lastrevid":57730593,"modified":"2026-04-01T03:43:37Z","type":"item","id":"Q2129661","labels":{"en":{"language":"en","value":"A note on optimization formulations of Markov decision processes"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7512733"}},"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":"Q2129661$0DE3B5C6-6B57-41CD-AD90-26F9A880255D","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"80463f1274bd01d9921f66ecfc5819c5238d096c","datavalue":{"value":{"text":"A note on optimization formulations of Markov decision processes","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q2129661$1A97FD92-4C93-42EE-B227-E5163128BCD2","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"475ca1ed4363779d189abb92f645d067f5a0dc0d","datavalue":{"value":"1491.60123","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$971F8721-8185-43B5-B453-625616026C82","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"488111da21a16b149952154b1e12ca34fdf4ee79","datavalue":{"value":{"entity-type":"item","numeric-id":348572,"id":"Q348572"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2129661$7C8790F9-61EA-4DB7-87FB-93C8D628D329","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"15a4bfcf0bd6c32e705f362a338fbafc81665a33","datavalue":{"value":{"entity-type":"item","numeric-id":828490,"id":"Q828490"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2129661$81E67443-1AF2-4694-8A63-77D9F9331E05","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"9cf451b851aebd4109d99aac6e336aba55d7981f","datavalue":{"value":{"entity-type":"item","numeric-id":259348,"id":"Q259348"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2129661$AFD3541C-2E98-476E-A09D-D8963EB28D7D","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"6a2d220bbda83e730799716cad61153265e68ffa","datavalue":{"value":{"time":"+2022-04-22T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q2129661$8A81AA76-99C1-4339-9E89-2DF33F1942CE","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"35239094927ba13fe35924ac00fce77d665893b5","datavalue":{"value":"https://arxiv.org/abs/2012.09417","type":"string"},"datatype":"url"},"type":"statement","id":"Q2129661$40853776-4A87-4118-ADF7-C7C7C51DC572","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"b796392f6def29538fd4751068a54bcd20eb87eb","datavalue":{"value":"The paper summarizes the primal, primal-dual and dual problems for discounted standard Markov decision processes, discounted regularized Markov decision processes, undiscounted standard Markov decision processes and undiscounted regularized Markov decision processes. Moreover, the paper shows the equivalence between the dual problem and policy gradient as well as the equivalence between the primal problem and Bellman equation for the above four Markov decision processes. These optimization formulations are helpful for the theoretical study of Markov decision processes algorithms.","type":"string"},"datatype":"string"},"type":"statement","id":"Q2129661$BC4900CA-E4A0-4D6B-947F-023C602534EB","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"1cdf15533e26fc0c4c2e22d28e655c364dfe77a6","datavalue":{"value":"60J10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$9042DA4B-66DE-47A2-9246-0142C4932FF8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"69417b84cc431ede4e5ec12a55be58b45cd19ec0","datavalue":{"value":"60J22","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$9ACC14D4-78F9-423E-9C93-750855F75970","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"36d142e7ea03446b1d7deb9627eedb9f0297f86a","datavalue":{"value":"90C05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$57AD4CB0-9478-4402-BC52-F5E575EFBF57","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"4799dbdfe8e7efdb8ca3cc985d12590b3e088667","datavalue":{"value":"7512733","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$505149CD-0CAF-4EB5-965D-7CA19935FDDE","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fbd1f99995fb6a13da62a377ba6327166316e976","datavalue":{"value":"Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q2129661$8962C7E7-11F6-4373-82E6-5434329697E2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"c27024bc3112e6fbf1cca0a9a4aacb8e7e4a77e0","datavalue":{"value":"optimization","type":"string"},"datatype":"string"},"type":"statement","id":"Q2129661$EE07E422-41BC-4324-993F-0FD45329D12E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"a08efa1a08a750d06fca0196004a17a02a35c592","datavalue":{"value":"linear programming","type":"string"},"datatype":"string"},"type":"statement","id":"Q2129661$1B595EEE-7AF7-44D3-B52D-7894DEFE763D","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"e221d798db97bd27768780e2e01d2077edf5eea4","datavalue":{"value":{"entity-type":"item","numeric-id":334011,"id":"Q334011"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2129661$9549B939-4F68-4EA4-ABB0-999A9094A059","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":"Q2129661$760194B1-97CB-4C53-AFAC-EB2256205BDB","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"73169860ab7b06d43009f47ec7e6cbea452cd0e7","datavalue":{"value":"W3111550499","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$D572E915-A9D6-4662-A988-85AF77B05212","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"a55ab04a896e0f3bc0752c9206ec79fb5e07249a","datavalue":{"value":"10.4310/CMS.2022.V20.N3.A5","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2129661$A45E2B87-86B2-45E8-A2BA-4886A350636B","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"9080c07510348e4ce07bcaf8b442e03cf4fd454d","datavalue":{"value":{"entity-type":"item","numeric-id":1075957,"id":"Q1075957"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"4b88db00e3401eb28ef522db30b2f09e6e19e3db","datavalue":{"value":{"amount":"+0.7356648445129395","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2129661$F9124C6F-333A-411A-A1BF-61165546A1E6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"c5eea3d6457ba2c539ccda9447ec585b5d7dc54c","datavalue":{"value":{"entity-type":"item","numeric-id":1728357,"id":"Q1728357"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"033ee57b5e16372a4997f942466fb5bdb1486fba","datavalue":{"value":{"amount":"+0.7248914241790771","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":"Q2129661$FD21C55B-153C-4198-98CE-45D9AFAA9F44","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"25f45a021a151e3238e75481c6e90e3913b60a54","datavalue":{"value":{"entity-type":"item","numeric-id":1969768,"id":"Q1969768"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"6cf7722e6f172159fec3157c977eb45604c017e6","datavalue":{"value":{"amount":"+0.7176705002784729","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":"Q2129661$0EAE59D9-DD92-4F21-90FA-DC9B3BA7A6CF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"7f1b2207be3d77a1010ef634380d5205dbcad50d","datavalue":{"value":{"entity-type":"item","numeric-id":3084852,"id":"Q3084852"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"c37e4c4ac079e4aedc531f3a9ae623285dfcd5a1","datavalue":{"value":{"amount":"+0.7169718146324158","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":"Q2129661$1BC0DB8A-298C-4D7D-9571-E56B46E84F9E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"bc9697b968fed6fbe434e9fe821fd816e7f7ccef","datavalue":{"value":{"entity-type":"item","numeric-id":4315289,"id":"Q4315289"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"ad4fd1e43c2936d47db604c27c427f52ec6e8886","datavalue":{"value":{"amount":"+0.7132405042648315","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":"Q2129661$59207B87-C4F0-4854-90C2-A902E14C91B7","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Publication:2129661","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Publication:2129661"}}}}}