No label defined (Q4035208)
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 176107
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 176107 |
Statements
18 May 1993
0 references
multiplicative rewards
0 references
maximal growth rate
0 references
constraints
0 references
average reward Markov decision problems
0 references
optimal stationary policies
0 references
growth rate
0 references
0.8621259927749634
0 references
0.8603158593177795
0 references
0.8556699156761169
0 references
0.8512110710144043
0 references
[For the entire collection see Zbl 0752.00048.] For usual average reward Markov decision problems (MDPs) with a constraint based on a second reward structure of the same type there exist optimal stationary policies which are randomized for only one state. The same result is shown here for maximizing the growth rate in multiplicative MDPs, using monotonicity of the growth rate in the randomizing parameter (instead of linearity which holds in the additive case).
0 references
