Identification of optimal policies in Markov decision processes

Title:

Identification of optimal policies in Markov decision processes

Creator:

Sladký, Karel

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:eee6b805-eaf7-4211-aa9d-9885c8790391
uuid:eee6b805-eaf7-4211-aa9d-9885c8790391

Subject:

finite state Markov decision processes, discounted and average costs, and elimination of suboptimal policies

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

In this note we focus attention on identifying optimal policies and on elimination suboptimal policies minimizing optimality criteria in discrete-time Markov decision processes with finite state space and compact action set. We present unified approach to value iteration algorithms that enables to generate lower and upper bounds on optimal values, as well as on the current policy. Using the modified value iterations it is possible to eliminate suboptimal actions and to identify an optimal policy or nearly optimal policies in a finite number of steps without knowing precise values of the performance function.

Language:

English

Rights:

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

Coverage:

[558]-570

Source:

Kybernetika | 2010 Volume:46 | Number:3

Harvested from:

CDK

Metadata only:

false