Time-Driven Scheduling Based on Reinforcement Learning for Reasoning Tasks in Vehicle Edge Computing

Table 4

Average runtime (s) of different algorithms with different seasoning tasks in various edge environments

Number of edge nodes	Algorithm	Topology I ()	Topology II ()	Topology II ()
	GA-PSO	0.53	0.76	2.02
	DQN	0.02	0.05	0.08
	Q-learning	0.02	0.06	0.44
	GA-PSO	0.58	0.72	1.19
	DQN	0.04	0.12	0.28
	Q-learning	0.10	0.58	11.36
	GA-PSO	0.61	0.83	0.93
	DQN	0.07	0.13	0.92
	Q-learning	0.19	7.77	11.29