Value iteration in average cost Markov control processes on Borel spaces (Q1906804)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Value iteration in average cost Markov control processes on Borel spaces |
scientific article; zbMATH DE number 841770
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Value iteration in average cost Markov control processes on Borel spaces |
scientific article; zbMATH DE number 841770 |
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
0 references
0 references
0 references
0 references
0 references
0 references
0.97283804
0 references
0.9519398
0 references
0.9285023
0 references
0.92822385
0 references
0.92165136
0 references
0.9209759
0 references
