Finitely Additive Dynamic Programming

• 成果类型: Article
• 署名作者: Sudderth, William D.
• 署名单位: University of Minnesota System; University of Minnesota Twin Cities
• 刊物名称: MATHEMATICS OF OPERATIONS RESEARCH
• ISSN/ISSBN: 0364-765X
• DOI: 10.1287/moor.2015.0717
• 发表日期: 2016
• 页码: 92-108
• 关键词: optimal reward operator; plans

摘要

The theory of dynamic programming is formulated using finitely additive probability measures defined on sets of arbitrary cardinality. Many results from the conventional countably additive theory generalize, and the proofs are simpler.