Research Article
Autonomous Navigation of the UAV through Deep Reinforcement Learning with Sensor Perception Enhancement
Table 2
The parameters of ANOAU algorithm.
| Parameter name | Value |
| | 0.1 | | 0.1 | | 0.01 | | 10 | | 3 | Learning rate | 1.0eā4 | Batch size | 32 | Optimizer | Adam | Activation function | tanh | Reward discount factor | 0.9 | N-step | 3 | of GAE | 0.97 | of ANOAU | 0.2 |
|
|