A stopping rule for discounted Markov decision processes with finite action sets

Title:

A stopping rule for discounted Markov decision processes with finite action sets

Creator:

Montes-de-Oca, Raúl, Lemus-Rodríguez, Enrique, and Cruz-Suárez, Daniel

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:1d5bba4a-e8cd-4766-9d81-13a51ff967c0
uuid:1d5bba4a-e8cd-4766-9d81-13a51ff967c0

Subject:

Markov decision process, ergodicity condition, value iteration, discounted cost, optimal policy, and myopic policies

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

In a Discounted Markov Decision Process (DMDP) with finite action sets the Value Iteration Algorithm, under suitable conditions, leads to an optimal policy in a finite number of steps. Determining an upper bound on the necessary number of steps till gaining convergence is an issue of great theoretical and practical interest as it would provide a computationally feasible stopping rule for value iteration as an algorithm for finding an optimal policy. In this paper we find such a bound depending only on structural properties of the Markov Decision Process, under mild standard conditions and an additional "individuality" condition, which is of interest in its own. It should be mentioned that other authors find such kind of constants using non-structural information, i.e., information not immediately apparent from the Decision Process itself. The DMDP is required to fulfill an ergodicity condition and the corresponding ergodicity index plays a critical role in the upper bound.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Coverage:

[755]-767

Source:

Kybernetika | 2009 Volume:45 | Number:5

Harvested from:

CDK

Metadata only:

false