Acceleration operators in the value iteration algorithms for Markov decision processes

Acceleration operators in the value iteration algorithms for Markov decision processes

0.00 Avg rating0 Votes
Article ID: iaor20101094
Volume: 58
Issue: 1
Start Page Number: 193
End Page Number: 202
Publication Date: Jan 2010
Journal: Operations Research
Authors: , , ,
Abstract:

We study the general approach to accelerating the convergence of the most widely used solution method of Markov decision processes (MDPs) with the total expected discounted reward. Inspired by the monotone behavior of the contraction mappings in the feasible set of the linear programming problem equivalent to the MDP, we establish a class of operators that can be used in combination with a contraction mapping operator in the standard value iteration algorithm and its variants. We then propose two such operators, which can be easily implemented as part of the value iteration algorithm and its variants. Numerical studies show that the computational savings can be significant especially when the discount factor approaches one and the transition probability matrix becomes dense, in which the standard value iteration algorithm and its variants suffer from slow convergence.

Reviews

Required fields are marked *. Your email address will not be published.