Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks

Table 3

Simulation parameters and values.

Category	Parameter	Value
SU	SU’s transmission delay, 𝑑^trSU	1.0 ms
	Processing delay, 𝑑^prSU	1.0 ms
	Mean arrival rate, 𝜆SU	0.6
	Learning rate, 𝛼	0.5
	WCRQ-routing weight factor, 𝜔	0.5
PU	PU’s transmission delay, 𝑑^trPU	1.2 ms
	Mean arrival rate (or PUL), 𝜇PUL	[0.0, 1.0]
	Standard deviation, 𝜎PUL	{0.0, 0.4, 0.8}
Channel	Mean PER, 𝜇PER	0.05
	Standard deviation of PER, 𝜎PER	0.025