Offline Reinforcement Learning under Gravity Shift on MuJoCo Ant
71.46Normalized ReturnCEDGE-Policy
Evaluation Results
| Method | Links | |
|---|---|---|
| CEDGE-PolicyLevel=5.02026.05 | 71.46 | |
| MOBODYLevel=5.02026.05 | 65.45 | |
| TCE(OG)Source Data=ant-m-e, Target Data=m2026.05 | 58 | |
| TCE(OG)Source Data=ant-m-e, Target Data=e2026.05 | 58 | |
| TCE(SM)Source Data=ant-m-r, Target Data=m2026.05 | 57.2 | |
| TCE(OG)Source Data=ant-m, Target Data=m2026.05 | 57 | |
| TCE(SM)Source Data=ant-m, Target Data=m2026.05 | 56.4 | |
| TCE(SM)Source Data=ant-m, Target Data=e2026.05 | 55.7 | |
| TCE(OG)Source Data=ant-m, Target Data=e2026.05 | 54.1 | |
| TCE(SM)Source Data=ant-m-e, Target Data=m2026.05 | 53.8 | |
| TCE(OG)Source Data=ant-m-r, Target Data=m2026.05 | 53.3 | |
| TCE(OG)Source Data=ant-m, Target Data=m-e2026.05 | 52.9 | |
| TCE(SM)Source Data=ant-m, Target Data=m-e2026.05 | 50.7 | |
| TCE(OG)Source Data=ant-m-r, Target Data=e2026.05 | 50.1 | |
| TCE(OG)Source Data=ant-m-e, Target Data=m-e2026.05 | 46 | |
| MOBODYLevel=2.02026.05 | 45.83 | |
| TCE(SM)Source Data=ant-m-e, Target Data=e2026.05 | 45.7 | |
| OTDFSource Data=ant-m, Target Data=m2026.05 | 45.1 | |
| CEDGE-PolicyLevel=2.02026.05 | 44.42 | |
| TCE(SM)Source Data=ant-m-r, Target Data=m-e2026.05 | 44 | |
| TCE(SM)Source Data=ant-m-e, Target Data=m-e2026.05 | 43.8 | |
| TCE(OG)Source Data=ant-m-r, Target Data=m-e2026.05 | 42.4 | |
| BOSALevel=2.02026.05 | 41.77 | |
| TCE(SM)Source Data=ant-m-r, Target Data=e2026.05 | 40.5 | |
| CEDGE-PolicyLevel=0.12026.05 | 37.99 | |
| MOBODYLevel=0.52026.05 | 37.44 | |
| IQLLevel=2.02026.05 | 37.17 | |
| MOBODYLevel=0.12026.05 | 37.09 | |
| DARALevel=2.02026.05 | 36.64 | |
| DiffuserLevel=2.02026.05 | 35.84 | |
| CEDGE-PolicyLevel=0.52026.05 | 35.16 | |
| CEDGE-PlannerLevel=2.02026.05 | 34.11 | |
| TD3-BCLevel=2.02026.05 | 34.04 | |
| OTDFSource Data=ant-m-e, Target Data=m-e2026.05 | 34 | |
| OTDFSource Data=ant-m, Target Data=m-e2026.05 | 33.9 | |
| OTDFSource Data=ant-m, Target Data=e2026.05 | 33.2 | |
| BOSALevel=5.02026.05 | 31.94 | |
| IQLLevel=5.02026.05 | 31.59 | |
| DARALevel=5.02026.05 | 31.01 | |
| OTDFSource Data=ant-m-r, Target Data=m2026.05 | 29.6 | |
| CEDGE-PlannerLevel=5.02026.05 | 27.42 | |
| BOSALevel=0.12026.05 | 25.58 | |
| OTDFSource Data=ant-m-r, Target Data=m-e2026.05 | 25.4 | |
| OTDFSource Data=ant-m-r, Target Data=e2026.05 | 24.5 | |
| OTDFSource Data=ant-m-e, Target Data=e2026.05 | 23.2 | |
| DARASource Data=ant-m-r, Target Data=m2026.05 | 21.7 | |
| IGDFSource Data=ant-m-r, Target Data=m-e2026.05 | 20.3 | |
| DARASource Data=ant-m-r, Target Data=e2026.05 | 20 | |
| SRPOSource Data=ant-m-r, Target Data=e2026.05 | 19.9 | |
| IGDFSource Data=ant-m-r, Target Data=m2026.05 | 19.6 | |
| IQL*Source Data=ant-m-r, Target Data=m-e2026.05 | 19.1 | |
| BOSALevel=0.52026.05 | 19.03 | |
| IQL*Source Data=ant-m-r, Target Data=m2026.05 | 18.9 | |
| IGDFSource Data=ant-m-r, Target Data=e2026.05 | 18.8 | |
| SRPOSource Data=ant-m-r, Target Data=m2026.05 | 18.7 | |
| SRPOSource Data=ant-m-r, Target Data=m-e2026.05 | 18.7 | |
| OTDFSource Data=ant-m-e, Target Data=m2026.05 | 18.6 | |
| IQL*Source Data=ant-m-r, Target Data=e2026.05 | 18.5 | |
| DARASource Data=ant-m-r, Target Data=m-e2026.05 | 18.3 | |
| BOSASource Data=ant-m-r, Target Data=m-e2026.05 | 15.9 | |
| BOSASource Data=ant-m-r, Target Data=e2026.05 | 14.5 | |
| BOSASource Data=ant-m-r, Target Data=m2026.05 | 13.9 | |
| TD3-BCLevel=0.12026.05 | 13.23 | |
| TD3-BCLevel=0.52026.05 | 12.91 | |
| IQLLevel=0.12026.05 | 12.53 | |
| DiffuserLevel=0.52026.05 | 12.44 | |
| BOSASource Data=ant-m, Target Data=m2026.05 | 12.4 | |
| DiffuserLevel=0.12026.05 | 11.92 | |
| BOSASource Data=ant-m, Target Data=e2026.05 | 11.8 | |
| SRPOSource Data=ant-m, Target Data=m2026.05 | 11.7 | |
| BOSASource Data=ant-m, Target Data=m-e2026.05 | 11.6 | |
| IGDFSource Data=ant-m, Target Data=m2026.05 | 11.3 | |
| CEDGE-PlannerLevel=0.12026.05 | 11.12 | |
| DARALevel=0.12026.05 | 11.03 | |
| DiffuserLevel=5.02026.05 | 10.46 | |
| DARASource Data=ant-m-e, Target Data=e2026.05 | 10.4 | |
| IQL*Source Data=ant-m, Target Data=m2026.05 | 10.2 | |
| SRPOSource Data=ant-m, Target Data=m-e2026.05 | 10.2 | |
| IQL*Source Data=ant-m, Target Data=e2026.05 | 10.2 | |
| IQLLevel=0.52026.05 | 10.09 | |
| DARASource Data=ant-m, Target Data=m-e2026.05 | 10 | |
| DARASource Data=ant-m, Target Data=e2026.05 | 9.8 | |
| IQL*Source Data=ant-m-e, Target Data=m2026.05 | 9.8 | |
| IGDFSource Data=ant-m, Target Data=e2026.05 | 9.7 | |
| SRPOSource Data=ant-m, Target Data=e2026.05 | 9.5 | |
| DARASource Data=ant-m, Target Data=m2026.05 | 9.4 | |
| IQL*Source Data=ant-m, Target Data=m-e2026.05 | 9.4 | |
| IGDFSource Data=ant-m, Target Data=m-e2026.05 | 9.4 | |
| IGDFSource Data=ant-m-e, Target Data=e2026.05 | 9.2 | |
| IQL*Source Data=ant-m-e, Target Data=e2026.05 | 9.1 | |
| DARALevel=0.52026.05 | 9.04 | |
| IQL*Source Data=ant-m-e, Target Data=m-e2026.05 | 9 | |
| IGDFSource Data=ant-m-e, Target Data=m2026.05 | 8.9 | |
| SRPOSource Data=ant-m-e, Target Data=e2026.05 | 8.8 | |
| SRPOSource Data=ant-m-e, Target Data=m2026.05 | 8.4 | |
| DARASource Data=ant-m-e, Target Data=m2026.05 | 8.1 | |
| BOSASource Data=ant-m-e, Target Data=m2026.05 | 8.1 | |
| IGDFSource Data=ant-m-e, Target Data=m-e2026.05 | 7.2 | |
| CEDGE-PlannerLevel=0.52026.05 | 7.13 | |
| DARASource Data=ant-m-e, Target Data=m-e2026.05 | 6.4 |