A vector minimum superharmonic approach to solving infinite-horizon discounted Markov decision processes

A vector minimum superharmonic approach to solving infinite-horizon discounted Markov decision processes

0.00 Avg rating0 Votes
Article ID: iaor19932373
Country: United Kingdom
Volume: 43
Issue: 11
Start Page Number: 1095
End Page Number: 1102
Publication Date: Nov 1992
Journal: Journal of the Operational Research Society
Authors:
Keywords: superharmonics
Abstract:

In this paper a new algorithm is provided for obtaining approximately optimal policies for infinite-horizon discounted Markov decision processes. In addition, some of the properties of the algorithm are established. The algorithm is based upon the fact that the optimal value function is the unqiue vector minimum function within the superharmonic set.

Reviews

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 Your email address will not be published.