Offline Reinforcement Learning on D4RL walker2d-medium-expert v2
115.4Normalized ScoreEDAC-10
Evaluation results
| Method | Links | |
|---|---|---|
| EDAC-102026.02 | 115.4 | |
| ADMModel category=Model-based2026.05 | 114.9 | |
| EDAC2022.10 | 114.7 | |
| EDAC2022.10 | 114.7 | |
| DMGModel category=Model-free2026.05 | 114.4 | |
| CPED2023.01 | 113.04 | |
| Onestep RL2023.01 | 113 | |
| Uncertainty-Aware Rank-One MIMO Q Network2026.02 | 112.9 | |
| PhyBModel category=Model-based2026.05 | 112.4 | |
| SPOT2023.01 | 112 | |
| EPQModel category=Model-free2026.05 | 112 | |
| PMDB2022.10 | 111.9 | |
| PMDBN=10, k=22022.10 | 111.9 | |
| PMDBModel category=Model-based2026.05 | 111.9 | |
| TD3+BC2023.01 | 110.1 | |
| TD3-BC2026.02 | 110.1 | |
| PBRL2026.02 | 110.1 | |
| IQL2023.01 | 109.6 | |
| IQL2026.02 | 109.6 | |
| CQL2022.10 | 109.1 | |
| CQL2022.10 | 109.1 | |
| CQLModel category=Model-free2026.05 | 109.1 | |
| CQL2023.01 | 108.8 | |
| TAILO2023.11 | 108.2 | |
| DT2023.01 | 108.1 | |
| CQL2026.02 | 107.9 | |
| MOREL2022.10 | 107.5 | |
| MOReL2022.10 | 107.5 | |
| BC2023.01 | 107.5 | |
| MOReLModel category=Model-based2026.05 | 107.5 | |
| BEAR2022.10 | 107 | |
| BEAR2022.10 | 107 | |
| TD3+BCModel category=Model-free2026.05 | 101.1 | |
| UWAV2026.02 | 96.5 | |
| MOReL2023.11 | 95.6 | |
| IQLShift Type=Kinematic2025.12 | 95.4 | |
| IGDFShift Type=Kinematic2025.12 | 90.6 | |
| BC2022.10 | 90.1 | |
| BC2022.10 | 90.1 | |
| DARAShift Type=Kinematic2025.12 | 85.3 | |
| DROCOShift Type=Kinematic2025.12 | 78.5 | |
| MOPO2026.02 | 77.4 | |
| AWAC2023.01 | 74.5 | |
| OTDFShift Type=Kinematic2025.12 | 63.1 | |
| CQLShift Type=Kinematic2025.12 | 61.4 | |
| RAMBO2022.10 | 56.7 | |
| RAMBOModel category=Model-based2026.05 | 56.7 | |
| MOPO2023.11 | 44.6 | |
| BCQ2026.02 | 43.6 | |
| BOSAShift Type=Kinematic2025.12 | 35.1 | |
| BEAR2026.02 | 22.1 | |
| BRAC2022.10 | 9.3 | |
| BRAC2022.10 | 9.3 | |
| FQLModel category=Model-free2026.05 | 7.3 |