Fig. 10From: Reinforcement learning-based dynamic band and channel selection in cognitive radio ad-hoc networksChannel movement example in Q-table. The update of the Q-table represents a unique pattern according to DDR by the reward for channel utilization efficiency proposed in this paper. The channel movement example of a low, b moderate, and c high DDR cases in Q-table is shown. The stable domain is in gray circle in each case of DDR. Each domain changes to another one by explore or natural transitionBack to article page