{"entities":{"Q7024072":{"pageid":21647331,"ns":120,"title":"Item:Q7024072","lastrevid":76731180,"modified":"2026-04-24T22:29:50Z","type":"item","id":"Q7024072","labels":{"en":{"language":"en","value":"A policy gradient algorithm for the risk-sensitive exponential cost MDP"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7987801"}},"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":"Q7024072$7C7077B0-2F2C-4396-B5D9-B01D03094DF5","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"c2a4822c0dd9e4247101570832f2eb3b6f31677c","datavalue":{"value":{"text":"A policy gradient algorithm for the risk-sensitive exponential cost MDP","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q7024072$1012FBBF-D566-429D-9C58-E6204E1603E8","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"d45dca34bff0f4646ceeee01dcd8d7832b2c6880","datavalue":{"value":"1558.60115","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7024072$775FE00D-88BF-4A8C-8EA9-54674A77F480","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"cd09eede514c79c2d0908c25003d691e0de019a8","datavalue":{"value":"10.1287/MOOR.2022.0139","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7024072$FD17F24B-673D-4F36-8ED2-C6B18E1B4843","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"3f162d768d80af059ebd21026ef47ccce56de27b","datavalue":{"value":{"entity-type":"item","numeric-id":2075324,"id":"Q2075324"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7024072$6B9A4CCA-42F3-412F-AA40-A024B870794B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"fbc29b37249beecef993f87b07a2f053a4d91657","datavalue":{"value":{"entity-type":"item","numeric-id":7024071,"id":"Q7024071"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7024072$883C037E-40C2-4FF4-B4BF-64CC44E2D81F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"807e747c1a483d0976aa1d62f67b7654fd634068","datavalue":{"value":{"entity-type":"item","numeric-id":5092298,"id":"Q5092298"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7024072$3C7591CF-BD07-46C9-80BE-CEF522AA78A6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"d98ebb135ac317393d5f806d77d8afa6001207e3","datavalue":{"value":{"entity-type":"item","numeric-id":1859085,"id":"Q1859085"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7024072$57F3C345-DF21-4F87-8E15-6911EF49D78B","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":"Q7024072$9F60B0CC-8A8F-427F-B860-A45A771FB1EB","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"ee822515221d44e64c31bd593541562252371a78","datavalue":{"value":{"time":"+2025-02-21T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7024072$43314631-F726-4AE9-A0FA-EDCA04C96A56","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"6a9ff1a146ff44dca747e334413377c148d2df3d","datavalue":{"value":"60J20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7024072$B5B1D8E9-83DB-4086-B28F-E8F25E8810FF","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"69417b84cc431ede4e5ec12a55be58b45cd19ec0","datavalue":{"value":"60J22","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7024072$70062145-4F2C-4791-9936-C2A6256FA5F6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"b23b4581d19061667c697da14a890aa055e6f323","datavalue":{"value":"65C40","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7024072$E12B4D32-CE4A-4712-A62E-1EBE3229A108","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"d33298b5b9444ef7088c74165c383bb5aa832f69","datavalue":{"value":"7987801","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7024072$DAB97195-AA7E-44A6-9C15-6027A6AABDD0","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"b17f57f1347c2041f3de057fa78d65f01dd26fc7","datavalue":{"value":"risk-sensitive Markov decision processes","type":"string"},"datatype":"string"},"type":"statement","id":"Q7024072$B8DF3B58-7E30-467E-BFB4-75F2F7A25803","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ab31482eee8f34fa99c5284980862acac4a0b6b4","datavalue":{"value":"reinforcement learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q7024072$E09CF343-8803-4E58-900B-70B8BE9AEE73","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"fff3b6140498b3437f45ac062df9687885be2490","datavalue":{"value":"policy gradient theorem","type":"string"},"datatype":"string"},"type":"statement","id":"Q7024072$7D16E7C2-D9E2-4D24-9AC4-54AE0BCBC140","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"7c907e87ef34df25ac1895768a34fab33458ac88","datavalue":{"value":"stochastic approximation","type":"string"},"datatype":"string"},"type":"statement","id":"Q7024072$8E1911FC-C242-412B-8F9F-2AE9A8393FF0","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7024072$DF03212A-BE32-4253-8FD1-08F6207AA097","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"A policy gradient algorithm for the risk-sensitive exponential cost MDP","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/A_policy_gradient_algorithm_for_the_risk-sensitive_exponential_cost_MDP"}}}}}