Representing and solving decision problems with limited information

• 成果类型: Article
• 署名作者: Lauritzen, SL; Nilsson, D
• 署名单位: Aalborg University
• 刊物名称: MANAGEMENT SCIENCE
• ISSN/ISSBN: 0025-1909
• DOI: 10.1287/mnsc.47.9.1235.9779
• 发表日期: 2001
• 页码: 1235-1251
• 关键词: local computation; message passing; optimal strategies; partially observed Markov decision process; single policy updating

摘要

We introduce the notion of LImited Memory Influence Diagram (LIMID) to describe multistage decision problems in which the traditional assumption of no forgetting is relaxed. This can be relevant in situations with multiple decision makers or when decisions must be prescribed under memory constraints, such as in partially observed Markov decision processes (POMDPs). We give an algorithm for improving any given strategy by local computation of single policy updates and investigate conditions for the resulting strategy to be optimal.