Offline Reinforcement Learning under Gravity Shift on MuJoCo Walker2d
65.2Normalized ReturnTCE(SM)
Evaluation Results
| Method | Links | |
|---|---|---|
| TCE(SM)Source Data=walk-m-e, Target Data=e2026.05 | 65.2 | |
| OTDFSource Data=walk-m-e, Target Data=e2026.05 | 61.1 | |
| DARASource Data=walk-m-e, Target Data=e2026.05 | 56.4 | |
| OTDFSource Data=walk-m-e, Target Data=m-e2026.05 | 53.3 | |
| IQL*Source Data=walk-m-e, Target Data=m-e2026.05 | 49.1 | |
| TCE(SM)Source Data=walk-m, Target Data=e2026.05 | 46.9 | |
| SRPOSource Data=walk-m-e, Target Data=m2026.05 | 46.4 | |
| DARASource Data=walk-m-e, Target Data=m-e2026.05 | 45.8 | |
| SRPOSource Data=walk-m-e, Target Data=e2026.05 | 45.8 | |
| TCE(SM)Source Data=walk-m-e, Target Data=m-e2026.05 | 45.6 | |
| IGDFSource Data=walk-m-e, Target Data=e2026.05 | 45.3 | |
| OTDFSource Data=walk-m, Target Data=m-e2026.05 | 44.8 | |
| IGDFSource Data=walk-m-e, Target Data=m-e2026.05 | 44.7 | |
| OTDFSource Data=walk-m, Target Data=e2026.05 | 44 | |
| BOSASource Data=walk-m-e, Target Data=e2026.05 | 43.7 | |
| TCE(SM)Source Data=walk-m-e, Target Data=m2026.05 | 43.2 | |
| DARASource Data=walk-m-e, Target Data=m2026.05 | 41.6 | |
| BOSASource Data=walk-m, Target Data=e2026.05 | 41.3 | |
| BOSASource Data=walk-m, Target Data=m-e2026.05 | 40.9 | |
| TCE(SM)Source Data=walk-m, Target Data=m-e2026.05 | 40.9 | |
| IQL*Source Data=walk-m-e, Target Data=e2026.05 | 40.4 | |
| BOSASource Data=walk-m-e, Target Data=m-e2026.05 | 40.1 | |
| IQL*Source Data=walk-m-e, Target Data=m2026.05 | 39.9 | |
| SRPOSource Data=walk-m, Target Data=e2026.05 | 39.5 | |
| BOSASource Data=walk-m, Target Data=m2026.05 | 38 | |
| IQL*Source Data=walk-m, Target Data=e2026.05 | 37.3 | |
| OTDFSource Data=walk-m, Target Data=m2026.05 | 36.6 | |
| TCE(SM)Source Data=walk-m, Target Data=m2026.05 | 36.6 | |
| SRPOSource Data=walk-m-e, Target Data=m-e2026.05 | 36.4 | |
| TCE(OG)Source Data=walk-m, Target Data=m2026.05 | 36.3 | |
| IGDFSource Data=walk-m, Target Data=e2026.05 | 36.2 | |
| DARASource Data=walk-m, Target Data=e2026.05 | 36 | |
| TCE(OG)Source Data=walk-m-r, Target Data=m2026.05 | 35.8 | |
| IQL*Source Data=walk-m, Target Data=m-e2026.05 | 35.7 | |
| IGDFSource Data=walk-m, Target Data=m-e2026.05 | 35.4 | |
| SRPOSource Data=walk-m, Target Data=m-e2026.05 | 34 | |
| IGDFSource Data=walk-m-e, Target Data=m2026.05 | 33.8 | |
| TCE(OG)Source Data=walk-m-e, Target Data=m2026.05 | 33 | |
| OTDFSource Data=walk-m-r, Target Data=m2026.05 | 32.7 | |
| BOSASource Data=walk-m-e, Target Data=m2026.05 | 32.3 | |
| OTDFSource Data=walk-m-r, Target Data=m-e2026.05 | 31.6 | |
| TCE(OG)Source Data=walk-m-e, Target Data=e2026.05 | 31.6 | |
| OTDFSource Data=walk-m-r, Target Data=e2026.05 | 31.3 | |
| DARASource Data=walk-m, Target Data=m-e2026.05 | 30.7 | |
| OTDFSource Data=walk-m-e, Target Data=m2026.05 | 30.2 | |
| TCE(OG)Source Data=walk-m-e, Target Data=m-e2026.05 | 28.6 | |
| DARASource Data=walk-m, Target Data=m2026.05 | 28.4 | |
| IQL*Source Data=walk-m, Target Data=m2026.05 | 28.1 | |
| TCE(OG)Source Data=walk-m-r, Target Data=m-e2026.05 | 27.4 | |
| IGDFSource Data=walk-m, Target Data=m2026.05 | 22.1 | |
| TCE(OG)Source Data=walk-m-r, Target Data=e2026.05 | 21.5 | |
| SRPOSource Data=walk-m, Target Data=m2026.05 | 21.4 | |
| TCE(OG)Source Data=walk-m, Target Data=m-e2026.05 | 20.6 | |
| TCE(OG)Source Data=walk-m, Target Data=e2026.05 | 20.3 | |
| TCE(SM)Source Data=walk-m-r, Target Data=m2026.05 | 20.3 | |
| TCE(SM)Source Data=walk-m-r, Target Data=m-e2026.05 | 18.2 | |
| SRPOSource Data=walk-m-r, Target Data=m2026.05 | 17.9 | |
| DARASource Data=walk-m-r, Target Data=m-e2026.05 | 15.9 | |
| IQL*Source Data=walk-m-r, Target Data=e2026.05 | 15.8 | |
| DARASource Data=walk-m-r, Target Data=e2026.05 | 15.7 | |
| TCE(SM)Source Data=walk-m-r, Target Data=e2026.05 | 15.6 | |
| IQL*Source Data=walk-m-r, Target Data=m-e2026.05 | 15.3 | |
| SRPOSource Data=walk-m-r, Target Data=m-e2026.05 | 15.3 | |
| IGDFSource Data=walk-m-r, Target Data=e2026.05 | 15.2 | |
| IQL*Source Data=walk-m-r, Target Data=m2026.05 | 14.6 | |
| DARASource Data=walk-m-r, Target Data=m2026.05 | 14.1 | |
| IGDFSource Data=walk-m-r, Target Data=m-e2026.05 | 13.9 | |
| SRPOSource Data=walk-m-r, Target Data=e2026.05 | 13.7 | |
| IGDFSource Data=walk-m-r, Target Data=m2026.05 | 11.6 | |
| BOSASource Data=walk-m-r, Target Data=m2026.05 | 7.6 | |
| BOSASource Data=walk-m-r, Target Data=e2026.05 | 7.1 | |
| BOSASource Data=walk-m-r, Target Data=m-e2026.05 | 4.8 |