Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes

It is proved that the optimal policy of a Markov decision process where the state space is truncated, will approximate the policy in case of no truncation.

Bibliographic Details
Main Author: Sjur D. Flåm
Format: Article
Language:English
Published: Norwegian Society of Automatic Control 1987-04-01
Series:Modeling, Identification and Control
Subjects:
Online Access:http://www.mic-journal.no/PDF/1987/MIC-1987-2-4.pdf