Optimal policy for minimizing risk models in Markov decision processes (Q1849140)
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 1836739
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Optimal policy for minimizing risk models in Markov decision processes |
scientific article; zbMATH DE number 1836739 |
Statements
Optimal policy for minimizing risk models in Markov decision processes (English)
0 references
28 November 2002
0 references
The referred paper deals with the discounted Markov decision processes with countable state space and non-negative bounded general rewards. The attention is focused on the minimizing risk problem, the optimal policy and the optimal values for finite and infinite horizon case. The main results show two sufficient conditions for the existence of an optimal policy in an infinite horizon case. One of them improves an incorrectness existing in the accessible literature. The existence of an optimal policy and the uniqueness of the solution of an optimality equation are shown under the conditions mentioned above.
0 references
Markov decision processes
0 references
decision making
0 references
minimizing risk model
0 references
maximal fixed point
0 references
optimal policy
0 references
0 references
0 references
0.8944523334503174
0 references
0.8840607404708862
0 references
0.8304383754730225
0 references
0.8174962401390076
0 references
