Offline Reinforcement Learning on MuJoCo Hopper Friction shift
52.94Normalized ScoreCEDGE-Policy
Evaluation Results
| Method | Links | |
|---|---|---|
| CEDGE-PolicyLevel=0.12026.05 | 52.94 | |
| MOBODYLevel=0.12026.05 | 51.19 | |
| CEDGE-PolicyLevel=0.52026.05 | 41.97 | |
| MOBODYLevel=0.52026.05 | 41.34 | |
| DiffuserLevel=0.52026.05 | 39.82 | |
| DiffuserLevel=0.12026.05 | 39.32 | |
| CEDGE-PlannerLevel=0.12026.05 | 36.65 | |
| CEDGE-PlannerLevel=0.52026.05 | 36.43 | |
| DARALevel=0.52026.05 | 26.94 | |
| DARALevel=0.12026.05 | 26.13 | |
| BOSALevel=0.12026.05 | 25.55 | |
| BOSALevel=0.52026.05 | 25.22 | |
| IQLLevel=0.12026.05 | 24.16 | |
| IQLLevel=0.52026.05 | 23.56 | |
| TD3-BCLevel=0.52026.05 | 19.6 | |
| TD3-BCLevel=0.12026.05 | 18.64 | |
| CEDGE-PlannerLevel=2.02026.05 | 14.06 | |
| DiffuserLevel=2.02026.05 | 11.09 | |
| CEDGE-PolicyLevel=2.02026.05 | 11.08 | |
| MOBODYLevel=2.02026.05 | 11 | |
| BOSALevel=2.02026.05 | 10.32 | |
| IQLLevel=2.02026.05 | 10.15 | |
| DARALevel=2.02026.05 | 10.15 | |
| TD3-BCLevel=2.02026.05 | 9.89 | |
| CEDGE-PlannerLevel=5.02026.05 | 8.27 | |
| CEDGE-PolicyLevel=5.02026.05 | 8.24 | |
| MOBODYLevel=5.02026.05 | 8.07 | |
| DiffuserLevel=5.02026.05 | 7.94 | |
| IQLLevel=5.02026.05 | 7.93 | |
| BOSALevel=5.02026.05 | 7.9 | |
| DARALevel=5.02026.05 | 7.86 | |
| TD3-BCLevel=5.02026.05 | 7.8 |