Research Article
Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks
Table 6
Simulation parameters and values for investigating the learning rate adjustment approaches.
| Category | Parameter | Value |
| SU | Best empirical learning rate, | {0.0064, 0.004} | Learning rate adjustment factor, | 0.001 | Learning rate range, | 0.001, 0.1 |
| PU | Standard deviation of PUL, | {0.2, 0.8} |
| Channel | Mean PER, | 0 | Standard deviation of PER, | 0 |
|
|