Review Article
Application of Reinforcement Learning in Cognitive Radio Networks: Models and Algorithms
Algorithm 4
RL algorithm for the channel auction scheme [
37].
Repeat | (a) Observe the current state and available channels | (b) Choose an action and submits it to the base station | (c) Receive channel allocation decision and the required channel cost | (d) Estimate the representative state and update the state transition probabilities of the other SUs | (e) Compute the estimated -value as follows: | | | (f) Update -table using learning rate as follows: | |
|