[Retracted] Intelligent Offloading Decision and Resource Allocations Schemes Based on RNN/DQN for Reliability Assurance in Software-Defined Massive Machine-Type Communications

Table 3

The summary of hyperparameter description.

Hyperparameters	Detailed value
Predicted length	Last 81 points
RNN specialist	LSTM
Number of neurons of input and output layers	50
Mini-batch size	32
Optimizer	Adam/SGD
Loss function	RMSE
Activation function of 1^st hidden layer	Tanh
Activation function of nth hidden layers	ReLu
Activation function of the output layer	Linear
Replay buffer	5000
	0.02
Discount factor
Optimal state space (threshold)
Policy	Boltzmann policy