Table 2 Algorithm parameters
From: Dynamic handoff policy for RAN slicing by exploiting deep reinforcement learning
Parameter | Value |
|---|---|
Number of input neurons | 8 |
Number of hidden neurons | 25 |
Number of output neurons | 1 |
Learning rate | 0.001 |
Exploration parameter ε | 0.1 |
C | 5 |
discount factor γ | 0.9 |