Reinforcement Learning on Ant v5 (Average AUC z-scored)
2.24Average AUC (z-scored)TD3
Evaluation Results
| Method | Links | |
|---|---|---|
| TD3Noise Type=OU2026.06 | 2.24 | |
| SACNoise Type=Red2026.06 | 0.86 | |
| TD3Noise Type=White2026.06 | 0.76 | |
| SACNoise Type=Pink2026.06 | 0.45 | |
| TD3Noise Type=Pink2026.06 | 0.43 | |
| TD3Noise Type=Baby2026.06 | 0.38 | |
| TD3Noise Type=Rose2026.06 | 0.31 | |
| TD3Noise Type=Red2026.06 | 0.29 | |
| SACNoise Type=Blush2026.06 | 0.28 | |
| SACNoise Type=White2026.06 | 0.17 | |
| SACNoise Type=Rose2026.06 | 0.07 | |
| TD3Noise Type=Blush2026.06 | 0.07 | |
| SACNoise Type=Baby2026.06 | 0.03 |