Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control (Q875484)
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: Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control |
scientific article; zbMATH DE number 5142370
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control |
scientific article; zbMATH DE number 5142370 |
Statements
Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control (English)
0 references
13 April 2007
0 references
adaptive critics
0 references
approximate dynamic programming
0 references
zero-sum games
0 references
policy iterations
0 references
\(H_{\infty }\) optimal control
0 references
\(Q\)-function
0 references
\(Q\)-learning
0 references
adaptive control
0 references
0 references
0.93027335
0 references
0.9017105
0 references
0.8908881
0 references
0 references
0 references
0.8723362
0 references
0.8681554
0 references
0.8667822
0 references
0.8667316
0 references
