Application of Reinforcement Learning in Cognitive Radio Networks: Models and Algorithms

Table 5

RL model for the routing scheme [33].

State	𝑠^𝑖𝑡∈𝑆={1,2,…,𝑁−1}; each state represents a SU destination node 𝑛. 𝑁 represents the number of SUs in the entire network
Action	𝑎^𝑖𝑡∈𝐴={1,2,…,𝐽}; each action represents the selection of a next-hop SU node 𝑗. 𝐽 represents the number of SU node 𝑖’s neighbor SUs
Reward	𝑟^𝑖𝑡+1𝑠^𝑖𝑡+1,𝑎^𝑖𝑡+1 represents the number of available common channels among nodes 𝑖 and 𝑗