Sample path optimality for a Markov optimization problem (Q2485850)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 2192584
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Sample path optimality for a Markov optimization problem |
scientific article; zbMATH DE number 2192584 |
Statements
Sample path optimality for a Markov optimization problem (English)
0 references
5 August 2005
0 references
A controlled Markov chain with long-term expected average cost criterion is considered. Sufficient conditions are given under which an optimal stationary policy is also asymptotically optimal with respect to the sample path cost criterion.
0 references
Markov decision process
0 references
Stochastic control
0 references
Azuma's inequality
0 references
0 references
0.8742185831069946
0 references
0.8356069922447205
0 references
0.8356069922447205
0 references
0.8301804065704346
0 references
