Deterministic policies based on maximum regrets in MDPs with imprecise rewards (Q5069649)
From MaRDI portal
scientific article; zbMATH DE number 7509003
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Deterministic policies based on maximum regrets in MDPs with imprecise rewards |
scientific article; zbMATH DE number 7509003 |
Statements
Deterministic policies based on maximum regrets in MDPs with imprecise rewards (English)
0 references
19 April 2022
0 references
Markov decision process
0 references
minimax regret
0 references
unknown rewards
0 references
branch-and-bound
0 references
deterministic policy
0 references
stochastic policy
0 references
0 references
0 references
