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

Table 3

RL model for joint dynamic channel selection and channel sensing [10].

Action	𝑎^𝑖𝑡∈𝐴𝑝=𝑎^𝑖𝑡∈𝐴∣𝑄^𝑖𝑡𝑎^𝑖𝑡>𝑄th; each action represents a single channel available for data transmission
Reward	𝑟^𝑖𝑡+1𝑎^𝑖𝑡=1,ifsuccessfultransmission−1,ifunsuccessfultransmission