Offline Reinforcement Learning on D4RL Locomotion Suite
91.1Average Normalized ScoreDQL
Evaluation results
| Method | Links | |
|---|---|---|
| DQLNFE=52026.03 | 91.1 | |
| KDPNFE=12026.03 | 90.7 | |
| ReBRACPolicy Category=Gaussian2026.05 | 90 | |
| CACNFE=22026.03 | 88 | |
| SRPOPolicy Category=Diffusion2026.05 | 87 | |
| AdaptDiffuserCategory=Diffusion Planner2024.05 | 83.4 | |
| DiffuserNFE=202026.03 | 82.6 | |
| TT2026.03 | 82.3 | |
| COMBOCategory=Model-based RL2024.05 | 82.03 | |
| IQLPolicy Category=Gaussian2026.05 | 82 | |
| IDQLPolicy Category=Diffusion2026.05 | 82 | |
| DDCategory=Diffusion Planner2024.05 | 81.8 | |
| DT2026.03 | 81.1 | |
| DriftQLPolicy Category=Drift2026.05 | 81 | |
| CQL2026.03 | 80.1 | |
| IQL2026.03 | 80 | |
| MOReL2026.03 | 78.8 | |
| DiffuserCategory=Diffusion Planner2024.05 | 77.5 | |
| MORELCategory=Model-based RL2024.05 | 72.72 | |
| CBCNFE=22026.03 | 69.9 | |
| BC2026.03 | 64.3 | |
| FQLPolicy Category=Flow2026.05 | 63 | |
| MBOP2026.03 | 60.9 | |
| BCPolicy Category=Gaussian2026.05 | 50 | |
| IFQLPolicy Category=Flow2026.05 | 50 | |
| MOPOCategory=Model-based RL2024.05 | 42.6 | |
| MOPO2026.03 | 36.6 |