From: Intelligent deep reinforcement learning-based scheduling in relay-based HetNets
Parameters | Values |
---|---|
K | 100 |
T | 128 |
Z | 32 |
M | 10 |
\(\epsilon _0\) | 0.1 |
\(\epsilon _{\rm min}\) | 0.001 |
\(\alpha _{\epsilon }\) | 2000 |
\(\gamma\) | 0.99 |
Optimizer | Adam |
Activation Function | ReLU |
Learning rate | \(10^{-4}\) |
Experience replay memory size | \(10^4\) |