A class of procedures to compute the optimal value f unction in a Markovian decision problem (Q3725896)
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 3956844
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A class of procedures to compute the optimal value f unction in a Markovian decision problem |
scientific article; zbMATH DE number 3956844 |
Statements
A class of procedures to compute the optimal value f unction in a Markovian decision problem (English)
0 references
1986
0 references
improving the convergence rate
0 references
successive approximation method
0 references
finite state Markov decision processes
0 references
finite expected discounted or non- discounted rewards
0 references
effective computation of the value function
0 references
0.92702043
0 references
0.89219683
0 references
0.88413846
0 references
0.8813007
0 references
0.8796598
0 references
0.8792871
0 references
