Reinforcement Learning on InvertedDoublePendulum v5
1.29Avg AUC (z-scored)TD3
Evaluation results
| Method | Links | |
|---|---|---|
| TD3Noise Type=OU2026.06 | 1.29 | |
| SACNoise Type=Red2026.06 | 0.95 | |
| TD3Noise Type=Pink2026.06 | 0.8 | |
| TD3Noise Type=Baby2026.06 | 0.53 | |
| TD3Noise Type=Red2026.06 | 0.43 | |
| SACNoise Type=Blush2026.06 | 0.31 | |
| SACNoise Type=Baby2026.06 | 0.25 | |
| SACNoise Type=White2026.06 | 0.23 | |
| SACNoise Type=Rose2026.06 | 0.23 | |
| TD3Noise Type=Rose2026.06 | 0.19 | |
| TD3Noise Type=Blush2026.06 | 0.18 | |
| SACNoise Type=Pink2026.06 | 0.07 | |
| TD3Noise Type=White2026.06 | 0.02 |