Deep Grid Scheduler for 5G NB-IoT Uplink Transmission

Algorithm 1

Procedure of double deep Q network.

	Initialize the evaluation network and target network
for episode in episodes do
initialize and choose state from NB-IoT MAC
while episode not end do
sampling and get action
observation from NB-IoT MAC and get reward and next state
store experience
update
if batch size ≥ memory capacity then
update
end if
end while
end for