{"entities":{"Q5962027":{"pageid":8138829,"ns":120,"title":"Item:Q5962027","lastrevid":97776089,"modified":"2026-06-05T15:24:00Z","type":"item","id":"Q5962027","labels":{"en":{"language":"en","value":"On-line policy gradient estimation with multi-step sampling"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 5786411"}},"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":"Q5962027$6E65124A-0002-4B47-AFD3-EE23774DCC4B","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"8516c2a68a04ff1499e6af630b35ea44c99ac46c","datavalue":{"value":{"text":"On-line policy gradient estimation with multi-step sampling","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q5962027$CB8E3864-605A-4435-A614-8991769C0018","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"e25e298df9d806bca54f649a75847733252a3249","datavalue":{"value":"1210.62113","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5962027$2198FFC8-BC52-4674-A489-94945C8D754F","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"65f4dc7a01ec7d847008d8bd9091a7ad355c6618","datavalue":{"value":{"entity-type":"item","numeric-id":243738,"id":"Q243738"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$E866C7CB-C5A3-4827-A350-0AC7AD182E6B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"95132ed570cae30f66d7ab6c820484335bcdc5d7","datavalue":{"value":{"entity-type":"item","numeric-id":243739,"id":"Q243739"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$7F9BC5FE-C4E0-4EB3-B1FF-F59A021B0494","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"646c4b950adcc2747e9b6d91c4105f879f76be24","datavalue":{"value":{"entity-type":"item","numeric-id":243740,"id":"Q243740"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$2F5E4A00-6130-4239-9F18-9F7C8F29F355","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"0f7c04b6b94cf13c193d472c226068c28e7c8f04","datavalue":{"value":{"entity-type":"item","numeric-id":169421,"id":"Q169421"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$4DFC394C-C8EB-4F12-80DD-301F066CC440","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"baf45dbcb13e63028464b24262c188c8428a543a","datavalue":{"value":{"time":"+2010-09-16T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q5962027$DE27227D-72A8-4856-8448-BE0709F2DEB0","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"7fe8cebe993754caf1c1a6489e3e16ad2b6350fb","datavalue":{"value":"The authors discuss the problem of sample-path-based (on-line) performance gradient estimation for Markov systems. The existing on-line performance gradient estimation algorithms generally require a standard importance sampling assumption. Examples are given to illustrate that the existing on-line policy gradient approaches cannot provide an accurate gradient estimate when the assumption does not hold. It is shown that this assumption can be relaxed and a few new algorithms are proposed based on multi-step sampling. These algorithms do not require this assumption. All the algorithms can be implemented on sample paths and policy gradients can be estimated on-line.","type":"string"},"datatype":"string"},"type":"statement","id":"Q5962027$2C283C1B-7743-41C4-AA6C-0B1EBDF62631","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"20136e68bc53d6cd8d1e4afb51ee5d9204386399","datavalue":{"value":{"entity-type":"item","numeric-id":589383,"id":"Q589383"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$EA6111E0-8CBD-42CD-87E9-1DB04CB9337D","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"5d625d780bfa809c5db39c69099009106c2aeb44","datavalue":{"value":"62M05","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5962027$3751587B-3886-4F1F-9C76-D9912817BE13","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"dd617f9d0fec58a219ee24586cc73ce6577bed23","datavalue":{"value":"65C60","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5962027$04D544B6-FD72-49F4-AF46-8518B13E8229","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"2358bdd46c44ce8518352913209de683a1e5ff06","datavalue":{"value":"5786411","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5962027$71B74226-4540-4C69-9359-6FB0B8125820","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"4cbbc041e4b7868cae592d23cc37ee2fcaaa64a0","datavalue":{"value":"Markov reward processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q5962027$C51F8A96-C958-4759-BC1C-BC970ABD4CFA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"87d329813f89256769dd0a7b797615974c0ccbee","datavalue":{"value":"on-line estimation","type":"string"},"datatype":"string"},"type":"statement","id":"Q5962027$14C318E0-9A84-4A8D-90E3-E448962C3364","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"7acfdc35aa76c43ed9f0615384fa93057940238e","datavalue":{"value":"performance potentials","type":"string"},"datatype":"string"},"type":"statement","id":"Q5962027$C64F4872-7D50-4E1C-9FC9-1FF35FC9D487","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":"Q5962027$EE287269-7A87-4C32-B5CD-359356A361CA","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"0f0f1f73bdf106abae59b06563b6270f9aebe002","datavalue":{"value":"https://doi.org/10.1007/s10626-009-0078-3","type":"string"},"datatype":"url"},"type":"statement","id":"Q5962027$15D947DE-C8DF-49C4-99AC-A19A3ED77B61","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"705c9f3262bbc40291ee66e1b60d709760d08676","datavalue":{"value":"W2155938881","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5962027$63D5C196-47DD-4B98-8A2E-440ADAD8A3C9","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"1db73f91800611c9ccc6ed92bf640db275f9ea60","datavalue":{"value":{"entity-type":"item","numeric-id":4533362,"id":"Q4533362"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$B45F02B5-5398-4630-BBF9-7C7578693542","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"2659a2ac19c5badd2b8f356c69ae8c8c67bfb6b7","datavalue":{"value":{"entity-type":"item","numeric-id":4533363,"id":"Q4533363"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$994B690B-F8BB-4BE6-87AE-25BCD9D2FF3F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"4bdc033a8a11daafae04b5ee1e2abe92992de812","datavalue":{"value":{"entity-type":"item","numeric-id":5274061,"id":"Q5274061"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$B286C6AC-1E31-48C4-B1D2-91D6F7A91297","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"9a9858ae6b594e85e812d8bf3c280c359a46f858","datavalue":{"value":{"entity-type":"item","numeric-id":4368697,"id":"Q4368697"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$4F80DB64-6E57-445F-8696-6F73BFFE0EAA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d82216c069c0d4e92b398f0b1f2381174e692ded","datavalue":{"value":{"entity-type":"item","numeric-id":4109064,"id":"Q4109064"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$0C318E23-1C70-428B-BD03-B4197D343AD9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"0a91df795842bf5c287fe2bc97ab0e9aecd6c6f2","datavalue":{"value":{"entity-type":"item","numeric-id":3093234,"id":"Q3093234"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$7DFDF838-7175-48E1-A17D-F7BF9F0F09F5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"c571a82a1cdec9915f5d55e732dfe5c30bcf52ef","datavalue":{"value":{"entity-type":"item","numeric-id":4540300,"id":"Q4540300"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q5962027$6A1FA072-92C7-4FCB-AF54-8AF95BE5121B","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":"Q5962027$8F638C8D-816A-410D-9574-B2429AAFC898","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"7c2b8cc23de3b2d46d46a346f4c5896cf7eded3f","datavalue":{"value":"10.1007/S10626-009-0078-3","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q5962027$D83B305A-0689-4823-B428-CE2DD6FD59BE","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"f41c3c594189416d2752cde2e03cc3591a3928fc","datavalue":{"value":{"entity-type":"item","numeric-id":4416041,"id":"Q4416041"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"052ef79ad81175b050854174d6b2cc88cdb7dfa4","datavalue":{"value":{"amount":"+0.76523357629776","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":"Q5962027$38980A65-A6F8-48FB-AAAD-04EEE0D42DB3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"82eb67f5e21cf5fcd42e081c4852c8371bbed0ff","datavalue":{"value":{"entity-type":"item","numeric-id":4533363,"id":"Q4533363"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"052ef79ad81175b050854174d6b2cc88cdb7dfa4","datavalue":{"value":{"amount":"+0.76523357629776","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":"Q5962027$86288D37-A126-4799-822F-806B4040EEC6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"e5d69940389ba447b47a8c16cc685f7ed1eccec3","datavalue":{"value":{"entity-type":"item","numeric-id":2253434,"id":"Q2253434"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"ce0b49d44eb9db293f3374744c4b97b4f5b80a9e","datavalue":{"value":{"amount":"+0.7623757123947144","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":"Q5962027$204AE638-9156-4F71-A0F8-7E0BCFB80319","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"c194a39612230702fb5e4eac2422a4273f23773e","datavalue":{"value":{"entity-type":"item","numeric-id":1870312,"id":"Q1870312"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"283518fe0cbcc8b6615f7c3b9fd48f08b6904714","datavalue":{"value":{"amount":"+0.7600080966949463","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q5962027$C62318FC-A6F8-4A24-8AA6-4D58E690D0B2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"7f29d2edaa9a4956095948b9ddaa33790219a26b","datavalue":{"value":{"entity-type":"item","numeric-id":3986172,"id":"Q3986172"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"50176956d4901e60183e0e46920d5cc053f0ec4b","datavalue":{"value":{"amount":"+0.7480514645576477","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":"Q5962027$0AA6E0F2-72A7-487F-A74E-182E96F58DF4","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"On-line policy gradient estimation with multi-step sampling","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/On-line_policy_gradient_estimation_with_multi-step_sampling"}}}}}