A Resource Allocation Scheme for Intelligent Tasks in Vehicular Networks

Table 2

Deep learning-based experiment parameters.

Parameters	Values
The learning factor	0.001
The discount factor	0.9
The update frequency of target -network	5
The maximum number of iterative steps	10^4
The size of replay buffer	200
The dimensions of input layer	4
The dimensions of hidden layer	10
The dimensions of output layer	3