FASTER DYNAMIC PROGRAMMING FOR MARKOV DECISION PROCESSES

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...

Full description

Bibliographic Details
Main Author: Dai, Peng
Format: Others
Published: UKnowledge 2007
Subjects:
Online Access:http://uknowledge.uky.edu/gradschool_theses/428
http://uknowledge.uky.edu/cgi/viewcontent.cgi?article=1431&context=gradschool_theses
Description
Summary: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.