Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach. (Q2798089)
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 6562213
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach. |
scientific article; zbMATH DE number 6562213 |
Statements
1 April 2016
0 references
discounted Markov decision processes
0 references
dynamic programming
0 references
unique optimal policy
0 references
non-uniqueness of optimal policies
0 references
Ekeland's variational principle
0 references
Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach. (English)
0 references
0.8712096214294434
0 references
0.8305950164794922
0 references
0.8222190737724304
0 references
