Traffic Status Prediction of Arterial Roads Based on the Deep Recurrent Q-Learning

Table 9

Parameter combinations for the third.

Group	Learning rate	Reward delay	Greedy	Optimal loss coefficient
c	0.01	0.9	0.3	0.067
f	0.03	0.9	0.3	0.060
g	0.05	0.9	0.3	0.061