[Retracted] Feudal Multiagent Reinforcement Learning for Interdomain Collaborative Routing Optimization

Table 2

Training parameters.

Parameters	Value
Optimizer	Adam
Actor learning rate	0.01
Critic learning rate	0.01
Minibatch size	512
Target update coefficient	0.01
Discount factor	0.95
Network hidden units	64
Activation function	ReLU
Memory pool size	10^6