{"title":"约束非仿射非零和博弈的事件触发智能批评设计","authors":"Lingzhi Hu, Ding Wang, Ning Gao, Mingming Zhao","doi":"10.1145/3505688.3505701","DOIUrl":null,"url":null,"abstract":"In this paper, we develop an event-triggered optimal learning algorithm based on the dual heuristic dynamic programming (DHP) framework to solve a constrained nonzero-sum game problem with discrete-time nonaffine dynamics. First, for two controllers in nonzero-sum games, we adopt different boundaries to constrain them, which ensures their independence. Then, the specific derivation process of the proposed algorithm is given by using the DHP technique. Meanwhile, an appropriate triggering condition is established to decrease the amount of computation. Finally, a simulation example is carried out to demonstrate the applicability of the constructed method. The event-based constrained control algorithm is able to substantially reduce the updating times of the control input, while still maintaining an impressive performance.","PeriodicalId":375528,"journal":{"name":"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Event-Triggered Intelligent Critic Design for Constrained Nonaffine Nonzero-Sum Games\",\"authors\":\"Lingzhi Hu, Ding Wang, Ning Gao, Mingming Zhao\",\"doi\":\"10.1145/3505688.3505701\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we develop an event-triggered optimal learning algorithm based on the dual heuristic dynamic programming (DHP) framework to solve a constrained nonzero-sum game problem with discrete-time nonaffine dynamics. First, for two controllers in nonzero-sum games, we adopt different boundaries to constrain them, which ensures their independence. Then, the specific derivation process of the proposed algorithm is given by using the DHP technique. Meanwhile, an appropriate triggering condition is established to decrease the amount of computation. Finally, a simulation example is carried out to demonstrate the applicability of the constructed method. The event-based constrained control algorithm is able to substantially reduce the updating times of the control input, while still maintaining an impressive performance.\",\"PeriodicalId\":375528,\"journal\":{\"name\":\"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3505688.3505701\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 7th International Conference on Robotics and Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3505688.3505701","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Event-Triggered Intelligent Critic Design for Constrained Nonaffine Nonzero-Sum Games
In this paper, we develop an event-triggered optimal learning algorithm based on the dual heuristic dynamic programming (DHP) framework to solve a constrained nonzero-sum game problem with discrete-time nonaffine dynamics. First, for two controllers in nonzero-sum games, we adopt different boundaries to constrain them, which ensures their independence. Then, the specific derivation process of the proposed algorithm is given by using the DHP technique. Meanwhile, an appropriate triggering condition is established to decrease the amount of computation. Finally, a simulation example is carried out to demonstrate the applicability of the constructed method. The event-based constrained control algorithm is able to substantially reduce the updating times of the control input, while still maintaining an impressive performance.