Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence (Q6161312)
From MaRDI portal
scientific article; zbMATH DE number 7702810
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence |
scientific article; zbMATH DE number 7702810 |
Statements
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence (English)
0 references
27 June 2023
0 references
policy mirror descent
0 references
Bregman divergence
0 references
regularization
0 references
policy optimization
0 references
0 references
0 references
