Cross-domain Offline Reinforcement Learning on MuJoCo Hopper
66Hopper Performance (m -> m)TCE(OG)
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| TCE(OG)2026.05 | 66 | 75.7 | 91.5 | 65.9 | 82.8 | 84.8 | 67.3 | 74.7 | 65 | |
| TCE(SM)2026.05 | 65.7 | 70.3 | 76 | 66.2 | 65.1 | 72.3 | 66 | 72.1 | 62.9 | |
| OTDF2026.05 | 65.6 | 55.4 | 35 | 35.5 | 47.5 | 49.9 | 65.3 | 38.6 | 29.9 | |
| SRPO2026.05 | 65.4 | 43.9 | 53.1 | 36.1 | 36 | 36.1 | 64.6 | 54.7 | 57.6 | |
| IGDF2026.05 | 65.3 | 51.1 | 87.4 | 35.9 | 36.1 | 36.1 | 65.2 | 62.9 | 52.8 | |
| IQL*2026.05 | 58.7 | 68.5 | 79.9 | 36 | 36.1 | 36 | 66 | 45.1 | 44.9 | |
| DARA2026.05 | 43.9 | 55.4 | 83.7 | 39.4 | 34.1 | 36.1 | 61.1 | 61.9 | 84.2 | |
| BOSA2026.05 | 12.3 | 15.6 | 14.8 | 3.2 | 4.4 | 3.7 | 35 | 13.9 | 12 |