Fig. 6From: Dynamic handoff policy for RAN slicing by exploiting deep reinforcement learningHandoff probability. We compare the handoff probability of different algorithms with the progress of the handover decision in this figure. In the initial stage of decision-making, the handoff probability number of DQN algorithm is higher than greedy, RSS and fixed algorithm. However, as the decision progresses, the handoff probability of DQN algorithm decreases quicklyBack to article page