A unified approach to time-aggregated Markov decision processes
Li, Yanjie; Wu, Xinyu
刊名AUTOMATICA
2016
英文摘要This paper presents a unified approach to time-aggregated Markov decision processes (MDPs) with an average cost criterion. The approach is based on a framework in which a time-aggregated MDP constitutesa semi-Markov decision process (SMDP). By analyzing the performance sensitivity formulas of this SMDP,a number of optimization algorithms for time aggregated MDPs, including those previously reported in the literature, can be developed in a simple and intuitive way
收录类别SCI
原文出处http://www.sciencedirect.com/science/article/pii/S0005109815005543
语种英语
内容类型期刊论文
源URL[http://ir.siat.ac.cn:8080/handle/172644/9898]  
专题深圳先进技术研究院_集成所
作者单位AUTOMATICA
推荐引用方式
GB/T 7714
Li, Yanjie,Wu, Xinyu. A unified approach to time-aggregated Markov decision processes[J]. AUTOMATICA,2016.
APA Li, Yanjie,&Wu, Xinyu.(2016).A unified approach to time-aggregated Markov decision processes.AUTOMATICA.
MLA Li, Yanjie,et al."A unified approach to time-aggregated Markov decision processes".AUTOMATICA (2016).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace