Research Article
Energy-Efficient UAV Trajectory Design with Information Freshness Constraint via Deep Reinforcement Learning
Table 2
The settings of the deep neural network.
| Symbol | Description | Value |
| | Learning rate | 0.4 | | Greedy coefficient | 0.05 | | Discount factor | 0.9 | | Normalized parameter for EE | | | Batch size | 64 | | Interval of training data | 3 |
|
|