ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

Table 1

ALBRL training hyperparameters.

Hyperparameters	Value
Actor learning rate	0.001
Optimizer	Adam
Target update rate	0.01
Target network parameter update frequency	1
Number of iterations	500
Replay buffer	32
Batch size	8
Reward discount factor	0.99
Exploration noise