Fig. 10From: Reinforcement learning-based hybrid spectrum resource allocation scheme for the high load of URLLC servicesLoss probability with \(D_{MAX} = 3\;{\text{ms}}\). The loss probabilities of the RL-based, Greedy, Random, SFF, and Tetris schemes with maximum delay constraint \(D_{MAX} = 3\;{\text{ms}}\). The x-axis is the load, and the y-axis is the loss probability in Eq. (5)Back to article page