Offline Reinforcement Learning on D4RL Adroit door-human
13.2Mean Normalized Score
EPQ
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 13.2 | |
2025.12 | 11.3 | |
2025.12 | 10.7 | |
2026.02 | 9.9 | |
2025.12 | 6.3 | |
2026.02 | 6 | |
2026.02 | 5.5 | |
2026.02 | 5 | |
2025.12 | 3.3 | |
2026.02 | 3.1 | |
2026.02 | 3 | |
2025.12 | 2.3 | |
2026.02 | 2.3 | |
2025.12 | 2 | |
2025.12 | 0 | |
2026.02 | 0 | |
2026.02 | 0 | |
2026.02 | 0 | |
2025.12 | -0.1 | |
2026.02 | -0.1 | |
2025.12 | -0.2 | |
2025.12 | -0.2 |