Regret Analysis of a Markov Policy Gradient Algorithm for Multiarm Bandits (Q6121638)
From MaRDI portal
scientific article; zbMATH DE number 7809870
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Regret Analysis of a Markov Policy Gradient Algorithm for Multiarm Bandits |
scientific article; zbMATH DE number 7809870 |
Statements
Regret Analysis of a Markov Policy Gradient Algorithm for Multiarm Bandits (English)
0 references
27 February 2024
0 references
regret
0 references
policy gradient
0 references
multiarm bandit
0 references
Markov chains
0 references
Foster-Lyapunov
0 references
