Offline Reinforcement Learning on D4RL v2 (MuJoCo M/MR/ME + Adroit Tasks)
87.6Average Score
DOIT
Updated 4d ago
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 87.6 | - | - | - | - | - | - | - | - | - | - | - | - | |
2026.02 | 86.6 | 98 | 96.9 | 108 | 54.1 | 47.6 | 93.5 | 86 | 84.4 | 110.7 | - | - | - | |
2026.02 | 86.3 | 82.4 | 100.7 | 110.7 | 50.6 | 47.5 | 96.1 | 85.1 | 94.3 | 109.7 | - | - | - | |
2026.02 | 86.1 | - | - | - | - | - | - | - | - | - | - | - | - | |
2026.02 | 82.1 | - | - | - | - | - | - | - | - | - | - | - | - | |
2026.02 | 80.2 | - | - | - | - | - | - | - | - | - | - | - | - | |
2026.02 | 76.9 | 66.3 | 94.7 | 91.5 | 47.4 | 44.2 | 86.7 | 78.3 | 73.9 | 109.6 | - | - | - | |
2026.02 | 75.3 | 58.5 | 96.8 | 107.2 | 44.2 | 42.2 | 79.8 | 79.7 | 61.2 | 108.4 | - | - | - | |
2026.01 | 58.1 | 69.2 | 45.9 | 81.3 | 46.3 | 43.1 | 46.9 | 65.9 | 55.4 | 96.3 | 55.5 | 85.3 | 5.8 | |
2026.01 | 49.5 | 55 | 45.1 | 27.9 | 28.5 | 34.4 | 22.3 | 54.7 | 29.5 | 61.3 | 91.5 | 117.8 | 25.9 | |
2026.01 | 38.9 | 60.9 | 23.5 | 56.6 | 43.3 | 27.7 | 37.2 | 47.3 | 27.6 | 50.9 | 5.7 | 85.7 | 0.3 | |
2026.01 | 35.8 | 61 | 16.2 | 51.7 | 35.6 | 34.1 | 14.3 | 34.2 | 17.7 | 38 | 51 | 71.5 | 4.3 | |
2026.01 | 31.8 | 50.1 | 13.2 | 43.2 | 41.7 | 16.3 | 39.7 | 54.1 | 13.8 | 26 | 31.3 | 41.2 | 10.7 | |
2026.01 | 30.9 | 55.6 | 19.1 | 36.8 | 42.8 | 26.3 | 33.1 | 53.7 | 15.5 | 42.5 | 10.2 | 35.8 | -1.1 | |
2026.01 | 26.3 | 55.9 | 12.5 | 49.7 | 37.1 | 23.6 | 32.4 | 5.9 | 34.4 | 56.5 | 8.3 | -0.1 | -0.3 | |
2026.01 | 24.4 | 28.8 | 19.7 | 38.2 | 40.2 | 25.2 | 33.7 | 25.4 | 2.5 | 35.1 | 33.8 | 9.5 | 0.6 | |
2026.01 | 15.5 | 30.7 | 11.3 | 22.6 | 25.9 | 29.1 | 23.5 | 11.2 | 9.3 | 12.4 | 0 | 9.5 | 0.6 |