Markus Holzleitner, Lukas Gruber, Jose A. Arjona-Medina, Johannes Brandstetter, S. Hochreiter
{"title":"用于PPO和方向舵的行动者-评价方法的收敛性证明","authors":"Markus Holzleitner, Lukas Gruber, Jose A. Arjona-Medina, Johannes Brandstetter, S. Hochreiter","doi":"10.1007/978-3-662-63519-3_5","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":133531,"journal":{"name":"Trans. Large Scale Data Knowl. Centered Syst.","volume":"119 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":"{\"title\":\"Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER\",\"authors\":\"Markus Holzleitner, Lukas Gruber, Jose A. Arjona-Medina, Johannes Brandstetter, S. Hochreiter\",\"doi\":\"10.1007/978-3-662-63519-3_5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\",\"PeriodicalId\":133531,\"journal\":{\"name\":\"Trans. Large Scale Data Knowl. Centered Syst.\",\"volume\":\"119 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"26\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Trans. Large Scale Data Knowl. Centered Syst.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/978-3-662-63519-3_5\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Trans. Large Scale Data Knowl. Centered Syst.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-662-63519-3_5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}