An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes (Q5704141)
From MaRDI portal
scientific article; zbMATH DE number 2228306
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes |
scientific article; zbMATH DE number 2228306 |
Statements
An Algorithm to Identify and Compute Average Optimal Policies in Multichain Markov Decision Processes (English)
0 references
11 November 2005
0 references
Markov decision process
0 references
long-run average cost
0 references
multichain MDP
0 references
communication classes, finite state space
0 references
computation algorithm
0 references
approximate optimal policies
0 references
optimal policies
0 references
compact action sets
0 references