Offline Reinforcement Learning on MuJoCo Walker2d Friction shift
76.96Normalized ScoreMOBODY
Evaluation Results
| Method | Links | |
|---|---|---|
| MOBODYLevel=0.52026.05 | 76.96 | |
| MOBODYLevel=2.02026.05 | 73.74 | |
| CEDGE-PolicyLevel=2.02026.05 | 73.05 | |
| DARALevel=2.02026.05 | 72.91 | |
| CEDGE-PlannerLevel=0.52026.05 | 70.36 | |
| CEDGE-PolicyLevel=0.52026.05 | 70.16 | |
| DARALevel=0.52026.05 | 68.81 | |
| TD3-BCLevel=2.02026.05 | 67.89 | |
| IQLLevel=0.52026.05 | 66.26 | |
| IQLLevel=2.02026.05 | 65.4 | |
| DiffuserLevel=0.52026.05 | 64.43 | |
| BOSALevel=0.52026.05 | 63.94 | |
| CEDGE-PolicyLevel=0.12026.05 | 61.66 | |
| CEDGE-PlannerLevel=2.02026.05 | 52.66 | |
| DiffuserLevel=2.02026.05 | 48.38 | |
| TD3-BCLevel=0.52026.05 | 45.01 | |
| BOSALevel=2.02026.05 | 39.06 | |
| CEDGE-PolicyLevel=5.02026.05 | 36.44 | |
| TD3-BCLevel=0.12026.05 | 29.6 | |
| MOBODYLevel=0.12026.05 | 28.23 | |
| MOBODYLevel=5.02026.05 | 27.38 | |
| BOSALevel=5.02026.05 | 10.07 | |
| DiffuserLevel=0.12026.05 | 9.32 | |
| CEDGE-PlannerLevel=0.12026.05 | 8.71 | |
| BOSALevel=0.12026.05 | 7.88 | |
| CEDGE-PlannerLevel=5.02026.05 | 6.19 | |
| TD3-BCLevel=5.02026.05 | 5.76 | |
| IQLLevel=0.12026.05 | 5.72 | |
| DARALevel=0.12026.05 | 5.65 | |
| IQLLevel=5.02026.05 | 5.39 | |
| DARALevel=5.02026.05 | 5.36 | |
| DiffuserLevel=5.02026.05 | 4.5 |