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

Table 11

RL model for a power control scheme [38].

Action	𝑎^𝑖𝑡∈𝐴={𝑎^𝑖sh,𝑎^𝑖mh}, with 𝑎^𝑖sh and 𝑎^𝑖mh being transmitting SU 𝑖’s packets to the SU destination node using single-hop transmission and multiplehop relaying, respectively
Reward	𝑟^𝑖𝑡+1𝑎^𝑖𝑡+1 represents the revenue obtained from the other SUs for relaying their packets. Higher rewards indicate higher transmission rate and transmission power of SU node 𝑖