Value iteration in average cost Markov control processes on Borel spaces (Q1906804): Difference between revisions
From MaRDI portal
Changed an Item |
Set profile property. |
||
Property / MaRDI profile type | |||
Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank |
Revision as of 06:12, 5 March 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Value iteration in average cost Markov control processes on Borel spaces |
scientific article |
Statements
Value iteration in average cost Markov control processes on Borel spaces (English)
0 references
6 February 1996
0 references
This paper deals with discrete-time Markov control processes with Borel state and control spaces, allowing unbounded costs and noncompact control constraint sets. For the average cost criterion, the authors proved that, under suitable conditions, the value iteration algorithm converges to the optimal average cost and obtained an optimal policy.
0 references
discrete-time
0 references
Markov control processes
0 references
average cost
0 references
value iteration
0 references