Table 1 The Dyna-Q-Max-Action algorithm numerical simulation parameters
From: Model-based optimal action selection for Dyna-Q reverberation suppression cognitive sonar
Num. | T(ms) | Doppler resolution (m/s) | Doppler clutter width (m/s) | \(\textrm{R}_{\text{ reward } }\) |
|---|---|---|---|---|
1 | 100 | 0.825 | 4.2 | \(-(2.55)^q\) |
2 | 150 | 0.55 | 2.7 | \(-(1.6)^q\) |
3 | 200 | 0.4125 | 2.2 | \(-(1.375)^q\) |
4 | 300 | 0.275 | 0.553 | 10 |
5 | 350 | 0.236 | 2 | \(-(1.528)^q\) |