Offline Reinforcement Learning on MuJoCo Ant Friction shift
62.41Normalized ScoreMOBODY
Evaluation Results
| Method | Links | |
|---|---|---|
| MOBODYLevel=0.52026.05 | 62.41 | |
| CEDGE-PolicyLevel=0.12026.05 | 61.85 | |
| CEDGE-PolicyLevel=5.02026.05 | 60.31 | |
| BOSALevel=0.52026.05 | 59.72 | |
| IQLLevel=0.52026.05 | 59.28 | |
| DiffuserLevel=0.52026.05 | 58.98 | |
| BOSALevel=0.12026.05 | 58.95 | |
| DARALevel=0.52026.05 | 58.92 | |
| MOBODYLevel=0.12026.05 | 58.79 | |
| CEDGE-PolicyLevel=2.02026.05 | 57.49 | |
| DiffuserLevel=0.12026.05 | 57.07 | |
| IQLLevel=0.12026.05 | 55.56 | |
| DARALevel=0.12026.05 | 55.12 | |
| CEDGE-PolicyLevel=0.52026.05 | 54.06 | |
| TD3-BCLevel=0.12026.05 | 49.2 | |
| CEDGE-PlannerLevel=0.12026.05 | 48.41 | |
| MOBODYLevel=2.02026.05 | 47.41 | |
| CEDGE-PlannerLevel=0.52026.05 | 42.36 | |
| MOBODYLevel=5.02026.05 | 31.17 | |
| DiffuserLevel=2.02026.05 | 27.41 | |
| TD3-BCLevel=0.52026.05 | 25.21 | |
| TD3-BCLevel=2.02026.05 | 22.69 | |
| BOSALevel=2.02026.05 | 20.18 | |
| IQLLevel=2.02026.05 | 19.84 | |
| DARALevel=2.02026.05 | 17.54 | |
| DiffuserLevel=5.02026.05 | 15.67 | |
| CEDGE-PlannerLevel=5.02026.05 | 12.48 | |
| CEDGE-PlannerLevel=2.02026.05 | 10.66 | |
| TD3-BCLevel=5.02026.05 | 10.06 | |
| BOSALevel=5.02026.05 | 9.07 | |
| DARALevel=5.02026.05 | 7.8 | |
| IQLLevel=5.02026.05 | 7.75 |