{"title":"具有重置作用的约束马尔可夫决策过程的次线性后悔强化学习算法","authors":"Takashi Watanabe, T. Sakuragawa","doi":"10.1145/3380688.3380706","DOIUrl":null,"url":null,"abstract":"In this paper, we study model-based reinforcement learning in an unknown constrained Markov Decision Processes (CMDPs) with reset action. We propose an algorithm, Constrained-UCRL, which uses confidence interval like UCRL2, and solves linear programming problem to compute policy at the start of each episode. We show that Constrained-UCRL achieves sublinear regret bounds Õ(SA1/2T3/4) up to logarithmic factors with high probability for both the gain and the constraint violations.","PeriodicalId":414793,"journal":{"name":"Proceedings of the 4th International Conference on Machine Learning and Soft Computing","volume":"140 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Sublinear-Regret Reinforcement Learning Algorithm on Constrained Markov Decision Processes with reset action\",\"authors\":\"Takashi Watanabe, T. Sakuragawa\",\"doi\":\"10.1145/3380688.3380706\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we study model-based reinforcement learning in an unknown constrained Markov Decision Processes (CMDPs) with reset action. We propose an algorithm, Constrained-UCRL, which uses confidence interval like UCRL2, and solves linear programming problem to compute policy at the start of each episode. We show that Constrained-UCRL achieves sublinear regret bounds Õ(SA1/2T3/4) up to logarithmic factors with high probability for both the gain and the constraint violations.\",\"PeriodicalId\":414793,\"journal\":{\"name\":\"Proceedings of the 4th International Conference on Machine Learning and Soft Computing\",\"volume\":\"140 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 4th International Conference on Machine Learning and Soft Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3380688.3380706\",\"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 4th International Conference on Machine Learning and Soft Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3380688.3380706","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Sublinear-Regret Reinforcement Learning Algorithm on Constrained Markov Decision Processes with reset action
In this paper, we study model-based reinforcement learning in an unknown constrained Markov Decision Processes (CMDPs) with reset action. We propose an algorithm, Constrained-UCRL, which uses confidence interval like UCRL2, and solves linear programming problem to compute policy at the start of each episode. We show that Constrained-UCRL achieves sublinear regret bounds Õ(SA1/2T3/4) up to logarithmic factors with high probability for both the gain and the constraint violations.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
