A counterexample on sample-path optimality in stable Markov decision chains with the average reward criterion (Q481787)
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: A counterexample on sample-path optimality in stable Markov decision chains with the average reward criterion |
scientific article; zbMATH DE number 6380451
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A counterexample on sample-path optimality in stable Markov decision chains with the average reward criterion |
scientific article; zbMATH DE number 6380451 |
Statements
A counterexample on sample-path optimality in stable Markov decision chains with the average reward criterion (English)
0 references
15 December 2014
0 references
strong sample-path optimality
0 references
Lyapunov function condition
0 references
stationary policy
0 references
expected average reward criterion
0 references
0 references
0 references
0.908128261566162
0 references
0.8783934116363525
0 references
0.8476840257644653
0 references
0.847440779209137
0 references
0.8382452726364136
0 references
