Research Article
A Method of Multi-UAV Cooperative Task Assignment Based on Reinforcement Learning
Table 2
The parameters of simulation.
| | Parameter | Value |
| | Number of UAVs | 3 | | Number of tasks | 3 | | Number of obstacles | 1 | | Number of base stations | 1 | | Steps of episode | 35 | | Capacity of replay buffer | 1000000 | | Number of network neurons | 128 | | Learning rate | 0.001 | | Discount factor of reward | 0.99 | | Update ratio of target network | 0.001 |
|
|
