基于损失函数和核的梯度改进策略控制算法

{"title":"基于损失函数和核的梯度改进策略控制算法","authors":"Matthew W. Robards, P. Sunehag","doi":"10.1007/978-3-642-29946-9_7","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Control\",\"authors\":\"Matthew W. Robards, P. Sunehag\",\"doi\":\"10.1007/978-3-642-29946-9_7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\",\"PeriodicalId\":432284,\"journal\":{\"name\":\"European Workshop on Reinforcement Learning\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Workshop on Reinforcement Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/978-3-642-29946-9_7\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Workshop on Reinforcement Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-642-29946-9_7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}