Reinforcement Learning on InvertedPendulum v5
1.77Avg AUC (z-scored)TD3
Evaluation results
| Method | Links | |
|---|---|---|
| TD3Noise Type=OU2026.06 | 1.77 | |
| SACNoise Type=Red2026.06 | 1.43 | |
| TD3Noise Type=Blush2026.06 | 0.62 | |
| SACNoise Type=Rose2026.06 | 0.59 | |
| TD3Noise Type=Rose2026.06 | 0.49 | |
| TD3Noise Type=Pink2026.06 | 0.49 | |
| SACNoise Type=White2026.06 | 0.39 | |
| TD3Noise Type=Red2026.06 | 0.36 | |
| TD3Noise Type=Baby2026.06 | 0.33 | |
| SACNoise Type=Pink2026.06 | 0.27 | |
| TD3Noise Type=White2026.06 | 0.21 | |
| SACNoise Type=Baby2026.06 | 0.13 | |
| SACNoise Type=Blush2026.06 | 0.06 |