Offline Reinforcement Learning on D4RL Adroit door-cloned
24Mean Normalized Score
MOBILE
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 24 | |
2025.12 | 15.3 | |
2025.12 | 9.6 | |
2025.12 | 5.8 | |
2026.02 | 5.8 | |
2026.02 | 4.1 | |
2025.12 | 3.1 | |
2026.02 | 2 | |
2026.02 | 1.3 | |
2026.02 | 1.1 | |
2026.02 | 1 | |
2026.02 | 0.8 | |
2026.02 | 0.4 | |
2026.02 | 0.2 | |
2025.12 | 0.1 | |
2026.02 | 0.1 | |
2025.12 | 0 | |
2026.02 | 0 | |
2026.02 | 0 | |
2025.12 | -0.1 | |
2025.12 | -0.1 |