Locomotion on D4RL hopper-medium-replay
1,993.8Test ReturnCOOPO
Evaluation Results
| Method | Links | |
|---|---|---|
| COOPO2026.05 | 1,993.8 | |
| Onestep RL2026.05 | 1,620.1 | |
| CQL2026.05 | 1,580.7 | |
| Uni-O42026.05 | 1,197.7 | |
| TD3+BC2026.05 | 1,016 | |
| IQL2026.05 | 913.2 | |
| Cal-QL2026.05 | 714.8 | |
| ODT2026.05 | 698.8 | |
| AWAC2026.05 | 624.2 | |
| PEX2026.05 | 360.3 | |
| Off2ON2026.05 | 322.1 | |
| BC2026.05 | 308.5 | |
| BiTrajDiffRL Algorithm=CQL2025.06 | 100.3 | |
| DiffStitchRL Algorithm=CQL2025.06 | 98.2 | |
| SyntherRL Algorithm=CQL2025.06 | 96.1 | |
| RTDiffRL Algorithm=CQL2025.06 | 95.9 | |
| BaseRL Algorithm=CQL2025.06 | 95.7 | |
| RTDiffRL Algorithm=DT2025.06 | 70.2 | |
| BiTrajDiffRL Algorithm=DT2025.06 | 69.6 | |
| SyntherRL Algorithm=DT2025.06 | 69 | |
| DiffStitchRL Algorithm=DT2025.06 | 68.1 | |
| BaseRL Algorithm=DT2025.06 | 67.3 |