Stabilizing Transmission Capacity in Millimeter Wave Links by Q-Learning-Based Scheme

Table 1

The comparison of the characteristics of the two types of learning algorithms.

The type of learning algorithm	Advantages	Disadvantages
Q-learning-based method	When the Q table is fully trained, the decision-making speed based on the Q table is very fast	Full training of the Q tables requires sufficient computing resources and takes a long time
Online learning solution	No training process is required, and thus training resources are saved	Decision process is slower than the well-trained Q table-based decision process