{"title":"离散时马尔可夫跳跃系统 H∞ 跟踪控制的强化 Q-learning 算法","authors":"Jiahui Shi, Dakuo He, Qiang Zhang","doi":"10.1080/00207721.2024.2395928","DOIUrl":null,"url":null,"abstract":"In this paper, the H∞ tracking control problem of linear discrete-time Markov jump systems is studied by using the data-based reinforcement learning method. Specifically, a new performance index fu...","PeriodicalId":14398,"journal":{"name":"International Journal of Systems Science","volume":"58 1","pages":""},"PeriodicalIF":4.9000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Reinforcement Q-learning algorithm for H∞ tracking control of discrete-time Markov jump systems\",\"authors\":\"Jiahui Shi, Dakuo He, Qiang Zhang\",\"doi\":\"10.1080/00207721.2024.2395928\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, the H∞ tracking control problem of linear discrete-time Markov jump systems is studied by using the data-based reinforcement learning method. Specifically, a new performance index fu...\",\"PeriodicalId\":14398,\"journal\":{\"name\":\"International Journal of Systems Science\",\"volume\":\"58 1\",\"pages\":\"\"},\"PeriodicalIF\":4.9000,\"publicationDate\":\"2024-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Systems Science\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1080/00207721.2024.2395928\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Systems Science","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1080/00207721.2024.2395928","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
Reinforcement Q-learning algorithm for H∞ tracking control of discrete-time Markov jump systems
In this paper, the H∞ tracking control problem of linear discrete-time Markov jump systems is studied by using the data-based reinforcement learning method. Specifically, a new performance index fu...
期刊介绍:
International Journal of Systems Science (IJSS) is a world leading journal dedicated to publishing high quality, rigorously reviewed, original papers that contribute to the methodology and practice in emerging systems engineering themes of intelligence, autonomy and complexity.
Modern systems are becoming more and more complex and sophisticated in their demand for performance, reliability and increasing autonomy. Historically, highly analytic and numeric-based methods have sufficed, frequently simplifying the problem to allow analytical tractability. Many manufactured and natural systems (biological, ecological and socio-economic) cannot be adequately represented or analyzed without requiring multiple interacting and interconnected frameworks and a common information-processing framework. A wide range of new theories, methodologies and techniques are required to ‘enable’ such systems, and thus engineering and integration to deal with these demands.
IJSS therefore encourages original submissions in these areas, with special focus on papers that are strongly novel as well as not being overly applied. Proposals for special issues in cutting-edge areas of systems science are encouraged, and should be discussed with the Editor-in-Chief.
Papers that cover those topics related to operations management and logistics will not be accepted for publication in IJSS. Instead they should be submitted directly to sister journal International Journal of Systems Science: Operations & Logistics.
Queries regarding submissions can be made by contacting the Editor-in-Chief, whose decision is final.