具有连续动作的马尔可夫决策过程的在线学习

{"title":"具有连续动作的马尔可夫决策过程的在线学习","authors":"Yi-Te Hong, Chi-Jen Lu","doi":"10.1007/978-3-319-24486-0_20","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":267197,"journal":{"name":"International Conference on Algorithmic Learning Theory","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Online Learning in Markov Decision Processes with Continuous Actions\",\"authors\":\"Yi-Te Hong, Chi-Jen Lu\",\"doi\":\"10.1007/978-3-319-24486-0_20\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\",\"PeriodicalId\":267197,\"journal\":{\"name\":\"International Conference on Algorithmic Learning Theory\",\"volume\":\"14 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-10-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Algorithmic Learning Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/978-3-319-24486-0_20\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Algorithmic Learning Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-319-24486-0_20","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}