文章基本信息

标题：Multiple-Environment Markov Decision Processes
本地全文：下载
作者：Jean-Francois Raskin ; Ocan Sankur
期刊名称：LIPIcs : Leibniz International Proceedings in Informatics
电子版ISSN：1868-8969
出版年度：2014
卷号：29
页码：531-543
DOI：10.4230/LIPIcs.FSTTCS.2014.531
出版社：Schloss Dagstuhl -- Leibniz-Zentrum fuer Informatik
摘要：We introduce Multi-Environment Markov Decision Processes (MEMDPs) which are MDPs with a set of probabilistic transition functions. The goal in an MEMDP is to synthesize a single controller strategy with guaranteed performances against all environments even though the environment is unknown a priori. While MEMDPs can be seen as a special class of partially observable MDPs, we show that several verification problems that are undecidable for partially observable MDPs, are decidable for MEMDPs and sometimes have even efficient solutions.
关键词：Markov decision processes; probabilistic systems; multiple objectives