A DRL-Based Intelligent Jamming Approach for Joint Channel and Power Optimization

Table 2

Parameter values used in the simulation.

Meaning	Parameter	Value
Discount factor		0.5
Initial exploration probability		0.95
Final exploration probability		0.05
Decay rate		0.0002
Learning rate		0.001
Communication time slot		100 ms
Spectrum sensing subslot		3 ms
Jamming emitting subslot		90 ms
Online learning subslot		2 ms
Jamming time slot		95 ms
Number of iterations		2900