Archived
This content is available here strictly for research, reference, and/or recordkeeping and as such it may not be fully accessible. If you work or study at University of Kentucky and would like to request an accessible version, please use the SensusAccess Document Converter.
Date Available
12-7-2011
Year of Publication
2007
Document Type
Thesis
College
Engineering
Department/School/Program
Computer Science
Faculty
Judy Goldsmith
Abstract
Markov decision processes (MDPs) are a general framework used by Artificial Intelligence (AI) researchers to model decision theoretic planning problems. Solving real world MDPs has been a major and challenging research topic in the AI literature. This paper discusses two main groups of approaches in solving MDPs. The first group of approaches combines the strategies of heuristic search and dynamic programming to expedite the convergence process. The second makes use of graphical structures in MDPs to decrease the effort of classic dynamic programming algorithms. Two new algorithms proposed by the author, MBLAO* and TVI, are described here.
Recommended Citation
Dai, Peng, "FASTER DYNAMIC PROGRAMMING FOR MARKOV DECISION PROCESSES" (2007). University of Kentucky Master's Theses. 428.
https://uknowledge.uky.edu/gradschool_theses/428
