Research Article
Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks
Table 4
Simulation parameters and values for investigating the effects of weight factor in reward representation.
| Category | Parameter | Value |
| SU | Mean arrival rate, | 0.8 |
| PU | Mean arrival rate (PUL), | {0.2, 0.4} | Standard deviation, | 0.5 |
| Channel | Mean PER, | {0.2, 0.4} | Standard deviation of PER, | 0.2 |
|
|