Skip to main content

Table 3 Target value and experimental parameter

From: Q-learning-based dynamic joint control of interference and transmission opportunities for cognitive radio

Target interference ratio
\( \left({R}_I^{\mathrm{th}}\right) \)
Target loss ratio
\( \left({R}_L^{\mathrm{th}}\right) \)
Parameters for reward
0.1 0.2 ρ1=3.15, ρ2=1.35, ω1=3, ω2=2, ϕ=25, K=40, L=30