Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems (Q6140987)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems |
scientific article; zbMATH DE number 7782638
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems |
scientific article; zbMATH DE number 7782638 |
Statements
Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems (English)
0 references
2 January 2024
0 references
reinforcement learning
0 references
policy gradient method
0 references
stochastic control
0 references
linear convergence
0 references
stationary point
0 references
backward stochastic differential equation
0 references
