On bidecision processes (Q1340581)
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: On bidecision processes |
scientific article; zbMATH DE number 703353
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | On bidecision processes |
scientific article; zbMATH DE number 703353 |
Statements
On bidecision processes (English)
0 references
14 December 1994
0 references
The author studies a (so-called) Markov bidecision process resulting from the standard Markov decision process by incorporating steps of maximization as well as minimization. With the help of an extended optimality equation he constructs a pair of policies, maximizing (resp. minimizing) the total reward in some sense. The pair of policies is found by a policy iteration method.
0 references
Markov bidecision process
0 references
extended optimality equation
0 references
policy iteration
0 references
