Offline Reinforcement Learning under Gravity Shift on MuJoCo Hopper
73.4Normalized ReturnTCE(OG)
Evaluation Results
| Method | Links | |
|---|---|---|
| TCE(OG)Source Data=hopp-m-r, Target Data=e2026.05 | 73.4 | |
| CEDGE-PolicyLevel=0.52026.05 | 68.25 | |
| TCE(OG)Source Data=hopp-m-e, Target Data=e2026.05 | 66.3 | |
| CEDGE-PlannerLevel=0.52026.05 | 63.28 | |
| TCE(OG)Source Data=hopp-m, Target Data=m2026.05 | 61.9 | |
| TCE(OG)Source Data=hopp-m-e, Target Data=m2026.05 | 61.3 | |
| TCE(OG)Source Data=hopp-m-r, Target Data=m2026.05 | 60.7 | |
| TCE(SM)Source Data=hopp-m-r, Target Data=m2026.05 | 58.3 | |
| TCE(SM)Source Data=hopp-m-e, Target Data=e2026.05 | 55.8 | |
| TCE(SM)Source Data=hopp-m-r, Target Data=e2026.05 | 55.7 | |
| TCE(SM)Source Data=hopp-m-e, Target Data=m2026.05 | 54 | |
| TCE(OG)Source Data=hopp-m, Target Data=e2026.05 | 53.4 | |
| TCE(SM)Source Data=hopp-m, Target Data=m2026.05 | 52.5 | |
| TCE(OG)Source Data=hopp-m, Target Data=m-e2026.05 | 46.2 | |
| TCE(OG)Source Data=hopp-m-e, Target Data=m-e2026.05 | 45.5 | |
| OTDFSource Data=hopp-m-e, Target Data=e2026.05 | 44.9 | |
| MOBODYLevel=0.12026.05 | 36.25 | |
| CEDGE-PolicyLevel=0.12026.05 | 36.02 | |
| TCE(SM)Source Data=hopp-m, Target Data=m-e2026.05 | 35 | |
| DiffuserLevel=0.52026.05 | 34.92 | |
| OTDFSource Data=hopp-m, Target Data=e2026.05 | 33.7 | |
| MOBODYLevel=0.52026.05 | 33.57 | |
| TCE(SM)Source Data=hopp-m-e, Target Data=m-e2026.05 | 33.4 | |
| TCE(SM)Source Data=hopp-m-r, Target Data=m-e2026.05 | 32.7 | |
| OTDFSource Data=hopp-m, Target Data=m2026.05 | 32.4 | |
| CEDGE-PlannerLevel=2.02026.05 | 31.38 | |
| OTDFSource Data=hopp-m-r, Target Data=m2026.05 | 31.1 | |
| OTDFSource Data=hopp-m-r, Target Data=e2026.05 | 31 | |
| CEDGE-PlannerLevel=0.12026.05 | 29.37 | |
| BOSALevel=0.52026.05 | 28.54 | |
| OTDFSource Data=hopp-m-e, Target Data=m-e2026.05 | 28.3 | |
| BOSALevel=0.12026.05 | 27.82 | |
| CEDGE-PolicyLevel=2.02026.05 | 26.94 | |
| OTDFSource Data=hopp-m-e, Target Data=m2026.05 | 26.4 | |
| IGDFSource Data=hopp-m-e, Target Data=e2026.05 | 26 | |
| DiffuserLevel=0.12026.05 | 25.59 | |
| OTDFSource Data=hopp-m, Target Data=m-e2026.05 | 24.2 | |
| OTDFSource Data=hopp-m-r, Target Data=m-e2026.05 | 24.2 | |
| TCE(OG)Source Data=hopp-m-r, Target Data=m-e2026.05 | 24.2 | |
| DARASource Data=hopp-m-e, Target Data=e2026.05 | 23.9 | |
| MOBODYLevel=2.02026.05 | 23.79 | |
| DARALevel=0.12026.05 | 23.4 | |
| BOSASource Data=hopp-m-e, Target Data=e2026.05 | 23.2 | |
| TD3-BCLevel=0.52026.05 | 23 | |
| IGDFSource Data=hopp-m-e, Target Data=m2026.05 | 22.3 | |
| SRPOSource Data=hopp-m-e, Target Data=e2026.05 | 21.4 | |
| BOSASource Data=hopp-m, Target Data=m-e2026.05 | 21.1 | |
| IQL*Source Data=hopp-m-e, Target Data=e2026.05 | 20.9 | |
| SRPOSource Data=hopp-m-e, Target Data=m2026.05 | 19.7 | |
| DARASource Data=hopp-m, Target Data=e2026.05 | 19.3 | |
| IQL*Source Data=hopp-m-e, Target Data=m2026.05 | 19.1 | |
| TCE(SM)Source Data=hopp-m, Target Data=e2026.05 | 18.9 | |
| TD3-BCLevel=2.02026.05 | 18.62 | |
| DARASource Data=hopp-m-e, Target Data=m2026.05 | 18.5 | |
| DARASource Data=hopp-m, Target Data=m2026.05 | 17.3 | |
| BOSASource Data=hopp-m-e, Target Data=m-e2026.05 | 17.3 | |
| IQL*Source Data=hopp-m-e, Target Data=m-e2026.05 | 16.8 | |
| IGDFSource Data=hopp-m-e, Target Data=m-e2026.05 | 16.6 | |
| SRPOSource Data=hopp-m-r, Target Data=e2026.05 | 16.4 | |
| IQLLevel=0.52026.05 | 16.24 | |
| IGDFSource Data=hopp-m-r, Target Data=e2026.05 | 16.1 | |
| IQLLevel=2.02026.05 | 16.1 | |
| DARASource Data=hopp-m-e, Target Data=m-e2026.05 | 16 | |
| BOSASource Data=hopp-m-e, Target Data=m2026.05 | 15.9 | |
| SRPOSource Data=hopp-m-e, Target Data=m-e2026.05 | 15.8 | |
| TD3-BCLevel=0.12026.05 | 15.59 | |
| DARASource Data=hopp-m, Target Data=m-e2026.05 | 15.4 | |
| IGDFSource Data=hopp-m-r, Target Data=m-e2026.05 | 15.4 | |
| IGDFSource Data=hopp-m, Target Data=m2026.05 | 15.3 | |
| IGDFSource Data=hopp-m-r, Target Data=m2026.05 | 15.3 | |
| BOSASource Data=hopp-m, Target Data=m2026.05 | 15.2 | |
| IGDFSource Data=hopp-m, Target Data=m-e2026.05 | 15.1 | |
| DiffuserLevel=2.02026.05 | 14.72 | |
| IQL*Source Data=hopp-m, Target Data=m-e2026.05 | 14.7 | |
| DARALevel=2.02026.05 | 14.65 | |
| IGDFSource Data=hopp-m, Target Data=e2026.05 | 14.4 | |
| SRPOSource Data=hopp-m-r, Target Data=m-e2026.05 | 14.4 | |
| DARASource Data=hopp-m-r, Target Data=e2026.05 | 14.3 | |
| SRPOSource Data=hopp-m, Target Data=m-e2026.05 | 14.2 | |
| SRPOSource Data=hopp-m-r, Target Data=m2026.05 | 14 | |
| IQL*Source Data=hopp-m-r, Target Data=m2026.05 | 13.9 | |
| IQL*Source Data=hopp-m-r, Target Data=m-e2026.05 | 13.3 | |
| IQLLevel=0.12026.05 | 13.1 | |
| DARALevel=0.52026.05 | 12.86 | |
| BOSASource Data=hopp-m, Target Data=e2026.05 | 12.7 | |
| IQL*Source Data=hopp-m, Target Data=e2026.05 | 12.5 | |
| DARASource Data=hopp-m-r, Target Data=m-e2026.05 | 12.5 | |
| SRPOSource Data=hopp-m, Target Data=m2026.05 | 12.4 | |
| BOSALevel=2.02026.05 | 11.84 | |
| SRPOSource Data=hopp-m, Target Data=e2026.05 | 11.8 | |
| IQL*Source Data=hopp-m, Target Data=m2026.05 | 11.2 | |
| IQL*Source Data=hopp-m-r, Target Data=e2026.05 | 11 | |
| DARASource Data=hopp-m-r, Target Data=m2026.05 | 10.7 | |
| TD3-BCLevel=5.02026.05 | 9.08 | |
| DiffuserLevel=5.02026.05 | 9 | |
| CEDGE-PolicyLevel=5.02026.05 | 8.8 | |
| CEDGE-PlannerLevel=5.02026.05 | 8.55 | |
| IQLLevel=5.02026.05 | 8.12 | |
| MOBODYLevel=5.02026.05 | 8.06 | |
| DARALevel=5.02026.05 | 7.9 |