Research Article
DQfD-AIPT: An Intelligent Penetration Testing Framework Incorporating Expert Demonstration Data
Table 5
Hyperparameter setting of the algorithm.
| Hyperparameter | DQfD | DQN |
| Batch size | 512 | 512 | Epsilon | 0.9 | 0.9 | Discount factor | 0.015 | 0.015 | Epsilon exponential decay | 5000 | 5000 | Epsilon minimum | 0.1 | 0.1 | Learning rate | 0.01 | 0.01 | Demonstration memory size | 1000 | | Replay memory size | 5000 | 5000 | Target network update frequency | 6 | 6 | Max steps per episode | 3000 | 3000 | Training episode | 200 | 200 |
|
|