Offline Reinforcement Learning on Adroit Pen (target-domain)
64.31Normalized Target-Domain Score
LoDADA
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 64.31 | |
2026.02 | 52.14 | |
2026.02 | 50.74 | |
2026.02 | 46.17 | |
2026.02 | 45.46 | |
2026.02 | 42.56 | |
2026.02 | 33.06 | |
2026.02 | 28.16 | |
2026.02 | 24.02 | |
2026.02 | 22.41 | |
2026.02 | 20.95 | |
2026.02 | 20.34 | |
2026.02 | 19.88 | |
2026.02 | 19.47 | |
2026.02 | 19.4 | |
2026.02 | 19.36 | |
2026.02 | 19.05 | |
2026.02 | 18.62 | |
2026.02 | 18.24 | |
2026.02 | 18.02 | |
2026.02 | 15.64 | |
2026.02 | 15.33 | |
2026.02 | 13.19 | |
2026.02 | 10.33 |