Research Article
A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning
Table 4
Controller parameters of system II.
| Parameter name | Description | Value |
| | Dimension of basis vector function for critic network. . | 100 | | Dimension of basis vector function for action network. . | 100 | | The width of radial basis function for critic network. . | 1.414 | | The width of radial basis function for action network. . | 1.414 | , | The center vector for basis function. . . . | Element distributed in | | The horizon length of strategy utility function. | 100 | | The update rate for critic network weight matrix. . | 0.001 | | The update rate for action network weight matrix. . | 0.03 | | The damping rate of tracking error. . | 0.01 |
|
|