Advances, Systems and Applications
Table 1 Main simulation parameters
From: PPO-based deployment and phase control for movable intelligent reflecting surface
Parameters | Values |
|---|---|
Number of AP antennas | 8 |
Number of IRS reflection units | 50 |
Height of base station (meters) | 2 |
actor learning rate | \(3 \times {10}^{-4}\) |
critic learning rate | \(3 \times {10}^{-4}\) |
Discount factor \(\gamma\) | 0.99 |
GAE parameters \(\lambda\) | 0.95 |
Renewal amplitude \(\varepsilon\) | 0.2 |
Hidden layer size | 64 |
Maximum training times | \(3 \times {10}^{6}\) |
Batch size | 2048 |
Mini batch size | 64 |