Anti-Attack Scheme for Edge Devices Based on Deep Reinforcement Learning

Table 2

Player’s mean payoff comparison.

Value	Data 1	Data 2	Data 3	Data 5
Mean payoff	21.251	20.448	20.775	15.849
Weight mean payoff	21.9937	21.219	21.5435	16.1693
Error	0.742695	0.771	0.7685	0.3203
Action	1	1	1	0