A note on policy algorithms for discounted Markov decision problems

A note on policy algorithms for discounted Markov decision problems

0.00 Avg rating—0 Votes
Article ID: iaor20052293
Country: Netherlands
Volume: 25
Issue: 4
Start Page Number: 195
End Page Number: 197
Publication Date: Nov 1999
Journal: Operations Research Letters
Authors:
Abstract:

In this note, we show that the evaluation phase in the policy iteration algorithm for the infinite horizon discounted Markov decision problem can be done in O(mN2) operations, where N is the number of states of the Markov decision process and m is the number of states in which the decision changes during the policy improvement phase.

Reviews

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 Your email address will not be published.