Offline Reinforcement Learning on D4RL halfcheetah v2 (medium-replay)
76.9Normalized ScoreCQL
Evaluation Results
| Method | Links | |
|---|---|---|
| CQL2022.10 | 76.9 | |
| PhyBModel category=Model-based2026.05 | 74.7 | |
| PMDB2022.10 | 71.7 | |
| PMDBN=10, k=22022.10 | 71.7 | |
| PMDBModel category=Model-based2026.05 | 71.7 | |
| MOPO2026.02 | 69.2 | |
| RAMBO2022.10 | 68.7 | |
| RAMBOModel category=Model-based2026.05 | 68.7 | |
| ADMModel category=Model-based2026.05 | 67.6 | |
| EPQModel category=Model-free2026.05 | 62 | |
| EDAC2022.10 | 61.3 | |
| EDAC2022.10 | 61.3 | |
| EDAC-102026.02 | 60.1 | |
| Uncertainty-Aware Rank-One MIMO Q Network2026.02 | 59.9 | |
| CPED2023.01 | 55.8 | |
| COMBOCategory=Model-based RL2024.05 | 55.1 | |
| MOPO2023.11 | 53.1 | |
| MOPOCategory=Model-based RL2024.05 | 53.1 | |
| SPOT2023.01 | 52.2 | |
| FQLModel category=Model-free2026.05 | 52.2 | |
| DMGModel category=Model-free2026.05 | 51.4 | |
| BEAR2022.10 | 48.6 | |
| BRAC2022.10 | 48.6 | |
| BRAC-v2026.01 | 47.7 | |
| CQL2026.01 | 46.2 | |
| CQL2023.01 | 45.5 | |
| CQL2026.02 | 45.5 | |
| BRAC2022.10 | 45.3 | |
| CQL2022.10 | 45.3 | |
| CQLModel category=Model-free2026.05 | 45.3 | |
| PBRL2026.02 | 45.1 | |
| TD3+BC2023.01 | 44.6 | |
| TD3+BC2026.01 | 44.6 | |
| TD3-BC2026.02 | 44.6 | |
| MOREL2022.10 | 44.5 | |
| MOReL2022.10 | 44.5 | |
| MOReLModel category=Model-based2026.05 | 44.5 | |
| IQL2023.01 | 44.2 | |
| IQL2026.01 | 44.2 | |
| TD3+BCModel category=Model-free2026.05 | 43.3 | |
| LSDT2026.01 | 42.9 | |
| TAILO2023.11 | 42.8 | |
| IQL2026.02 | 42.5 | |
| AWAC2023.01 | 40.5 | |
| MOReL2023.11 | 40.2 | |
| MORELCategory=Model-based RL2024.05 | 40.2 | |
| BEAR2022.10 | 39.4 | |
| VDT2026.01 | 39.4 | |
| DDCategory=Diffusion Planner2024.05 | 39.3 | |
| BCQ2026.02 | 39 | |
| AdaptDiffuserCategory=Diffusion Planner2024.05 | 38.3 | |
| Onestep RL2023.01 | 38.1 | |
| DDT2026.01 | 37.8 | |
| DiffuserCategory=Diffusion Planner2024.05 | 37.7 | |
| BC2022.10 | 37.6 | |
| BC2022.10 | 37.6 | |
| BC2023.01 | 36.6 | |
| DT2023.01 | 36.6 | |
| BEAR2026.02 | 36.3 | |
| DT2026.01 | 36.2 | |
| UWAV2026.02 | 35.9 | |
| DROCOShift Type=Kinematic2025.12 | 26.9 | |
| BOSAShift Type=Kinematic2025.12 | 26.3 | |
| CQLShift Type=Kinematic2025.12 | 23.6 | |
| IGDFShift Type=Kinematic2025.12 | 22.9 | |
| IQLShift Type=Kinematic2025.12 | 22.1 | |
| DARAShift Type=Kinematic2025.12 | 21.6 | |
| OTDFShift Type=Kinematic2025.12 | 15.6 |