Robust Markov Decision Processes
成果类型：
Article
署名作者：
Wiesemann, Wolfram; Kuhn, Daniel; Rustem, Berc
署名单位：
Imperial College London
刊物名称：
MATHEMATICS OF OPERATIONS RESEARCH
ISSN/ISSBN：
0364-765X
DOI：
10.1287/moor.1120.0566
发表日期：
2013
页码：
153-183
关键词：
摘要：
Markov decision processes (MDPs) are powerful tools for decision making in uncertain dynamic environments. However, the solutions of MDPs are of limited practical use because of their sensitivity to distributional model parameters, which are typically unknown and have to be estimated by the decision maker. To counter the detrimental effects of estimation errors, we consider robust MDPs that offer probabilistic guarantees in view of the unknown parameters. To this end, we assume that an observation history of the MDP is available. Based on this history, we derive a confidence region that contains the unknown parameters with a prespecified probability 1 - beta. Afterward, we determine a policy that attains the highest worst-case performance over this confidence region. By construction, this policy achieves or exceeds its worst-case performance with a confidence of at least 1 - beta. Our method involves the solution of tractable conic programs of moderate size.
来源URL：