\(H_\infty\) tracking control via variable gain gradient descent-based integral reinforcement learning for unknown continuous time non-linear system (Q6611594)
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: \(H_\infty\) tracking control via variable gain gradient descent-based integral reinforcement learning for unknown continuous time non-linear system |
scientific article; zbMATH DE number 7919479
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | \(H_\infty\) tracking control via variable gain gradient descent-based integral reinforcement learning for unknown continuous time non-linear system |
scientific article; zbMATH DE number 7919479 |
Statements
\(H_\infty\) tracking control via variable gain gradient descent-based integral reinforcement learning for unknown continuous time non-linear system (English)
0 references
26 September 2024
0 references
adaptive control
0 references
linear systems
0 references
iterative methods
0 references
continuous time systems
0 references
least squares approximations
0 references
learning systems
0 references
Lyapunov methods
0 references
optimal control
0 references
observers
0 references
learning (artificial intelligence)
0 references
neurocontrollers
0 references
gradient methods
0 references
nonlinear control systems
0 references
uncertain systems
0 references
variable gain gradient descent-based integral reinforcement
0 references
unknown continuous time nonlinear system
0 references
continuous-time nonlinear systems
0 references
system dynamics
0 references
optimal tracking problem
0 references
integral reinforcement learning
0 references
actor neural network
0 references
system performance
0 references
gradient descent-based parameter update scheme
0 references
real-time variation
0 references
plant dynamics
0 references
experience replay technique
0 references
NN weights
0 references
parameter update law
0 references
improved model-free tracking performance
0 references
\(H_\infty\) optimal tracking control
0 references
0 references
0 references
0 references
0 references
0 references
0 references
