MEAN-VARIANCE TRADEOFFS IN AN UNDISCOUNTED MDP - THE UNICHAIN CASE

• 成果类型: Article
• 署名作者: CHUNG, KJ
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.42.1.184
• 发表日期: 1994
• 页码: 184-188
• 关键词: decision analysis; RISK; MEAN-VARIANCE TRADEOFFS IN MDP; dynamic programming; Markov; FINITE STATE; MEAN-VARIANCE TRADEOFFS

摘要

The problem analyzed here is the computation of Pareto optima in the sense of high mean and low variance of the stationary distribution in the unichain, undiscounted Markov decision process (MDP, for short).