Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks

Algorithm 2

Counterapproach algorithm at SU node 𝑖.

initialize  𝛼𝑐^𝑝_𝑡+1++=[𝛼_min,𝛼_max]

while  (updating a new 𝑄-value 𝑄^𝑖_𝑡+1)

   if  (𝑄^𝑖_𝑡+1<𝑄^𝑖_𝑡)  then  𝑐^𝑝_𝑡+1++

   else  𝑐^𝑛_𝑡+1++

   end  if

  compute 𝑜^𝑛_𝑡+1=𝑐^𝑝_𝑡+1/𝑐^𝑛_𝑡+1

   if  (𝑜^𝑛_𝑡+1<1&&𝛼<𝛼_max)  then  𝛼+=𝑓

   else  if   (𝑜^𝑛_𝑡+1>1&&𝛼>𝛼_min)  then  𝛼−=𝑓

   end  if

end