Offline Reinforcement Learning on D4RL Medium Walker2d
106.4Normalized ScoreNEUBAY
Evaluation Results
| Method | Links | |
|---|---|---|
| NEUBAYMethod Category=Ours2025.12 | 106.4 | |
| PSPOAveraged across=4 random seeds2026.05 | 103.9 | |
| RRPINumber of random seeds=42026.03 | 97.5 | |
| CBOPMethod Category=Bayesian-inspired2025.12 | 95.5 | |
| CROPMethod Type=Model-based2023.10 | 95.4 | |
| MoMoMethod Category=Conservative model-based2025.12 | 95 | |
| PMDBNumber of random seeds=42026.03 | 94.2 | |
| PMDBMethod Type=Model-based2023.10 | 94.2 | |
| PMDB2026.05 | 94.2 | |
| SUMOMethod Category=Conservative model-based2025.12 | 94.1 | |
| ADMPOMethod Category=Conservative model-based2025.12 | 93.2 | |
| AMGNumber of random seeds=42026.03 | 93.2 | |
| ADM2026.05 | 93.2 | |
| VIPOMethod Category=Conservative model-based2025.12 | 93.1 | |
| EDACMethod Category=Model-free2025.12 | 92.5 | |
| EDACMethod Type=Model-free2023.10 | 92.5 | |
| DMGNumber of random seeds=42026.03 | 92.4 | |
| DMG2026.05 | 92.4 | |
| APE-VMethod Category=Conservative model-based2025.12 | 90.3 | |
| ATACMethod Type=Model-free2023.10 | 89.6 | |
| EPQNumber of random seeds=42026.03 | 87.8 | |
| EPQ2026.05 | 87.8 | |
| MOBILEMethod Category=Conservative model-based2025.12 | 87.7 | |
| Count-MORLMethod Type=Model-based2023.10 | 87.6 | |
| KDPNFE=12026.03 | 87.2 | |
| DQLNFE=52026.03 | 87 | |
| RAMBOMethod Type=Model-based2023.10 | 86.9 | |
| RAMBOMethod Category=Model-free2025.12 | 85 | |
| RAMBONumber of random seeds=42026.03 | 84.9 | |
| RAMBO2026.05 | 84.9 | |
| AdaptDiffuserCategory=Diffusion Planner2024.05 | 84.7 | |
| MOPOMethod Category=Conservative model-based2025.12 | 84.1 | |
| TD3+BCModel Category=Value-based2026.02 | 83.7 | |
| Decision Stacks2023.06 | 83.6 | |
| DMMModel Category=SSM-based2026.02 | 83.6 | |
| CACNFE=22026.03 | 83.1 | |
| CBCNFE=22026.03 | 83.1 | |
| DDImplementation=Original2023.06 | 82.5 | |
| DDCategory=Diffusion Planner2024.05 | 82.5 | |
| Decision Diffuser2025.12 | 82.5 | |
| CABI+TD3-BCMethod Type=Model-based2023.10 | 82 | |
| COMBOCategory=Model-based RL2024.05 | 81.9 | |
| COMBOMethod Category=Model-free2025.12 | 81.9 | |
| COMBO2025.12 | 81.9 | |
| COMBOMethod Type=Model-based2023.10 | 81.9 | |
| MAPLEMethod Category=Bayesian-inspired2025.12 | 81.3 | |
| MoDAPMethod Category=Bayesian-inspired2025.12 | 81.1 | |
| RATE2023.06 | 80.7 | |
| DMambasource=Lv et al., 20242023.06 | 80.3 | |
| IDQL2025.12 | 80.2 | |
| DDImplementation=reproduced2023.06 | 79.9 | |
| Diffuser2023.06 | 79.7 | |
| Diffuser2025.12 | 79.7 | |
| DiffuserCategory=Diffusion Planner2024.05 | 79.6 | |
| DCModel Category=SSM-based2026.02 | 79.6 | |
| DiffuserNFE=202026.03 | 79.6 | |
| CQLMethod Category=Model-free2025.12 | 79.5 | |
| CQLNumber of random seeds=42026.03 | 79.5 | |
| CQL2026.05 | 79.5 | |
| TT2023.06 | 79 | |
| TT2023.06 | 79 | |
| TT2026.03 | 79 | |
| IQL2023.06 | 78.3 | |
| IQL2026.03 | 78.3 | |
| IQLMethod Type=Model-free2023.10 | 78.3 | |
| DMambasource=Ota, 20242023.06 | 78.2 | |
| MambaDM2023.06 | 78.2 | |
| DS4Model Category=SSM-based2026.02 | 78 | |
| MOREL2023.06 | 77.8 | |
| MORELCategory=Model-based RL2024.05 | 77.8 | |
| MOReL2026.03 | 77.8 | |
| MPDiffuser+Rankranking=true2025.12 | 77.6 | |
| DMModel Category=SSM-based2026.02 | 77.6 | |
| MPDiffuserranking=false2025.12 | 77.5 | |
| DTModel Category=Transformer-based2026.02 | 76.6 | |
| D-MPC2025.12 | 76.2 | |
| Planner2025.12 | 75.9 | |
| EDTModel Category=Transformer-based2026.02 | 75.8 | |
| BC2023.06 | 75.3 | |
| BC2025.12 | 75.3 | |
| BC2026.03 | 75.3 | |
| LEQMethod Category=Conservative model-based2025.12 | 74.9 | |
| DT2023.06 | 74 | |
| DT2025.12 | 74 | |
| DT2023.06 | 74 | |
| DT2026.03 | 74 | |
| MOReLNumber of random seeds=42026.03 | 72.8 | |
| MOReL2026.05 | 72.8 | |
| CQL2023.06 | 72.5 | |
| CQLModel Category=Value-based2026.02 | 72.5 | |
| CQL2023.06 | 72.5 | |
| CQL2026.03 | 72.5 | |
| QLDTModel Category=Transformer-based2026.02 | 67.1 | |
| TAP2023.06 | 64.9 | |
| DROCO2025.12 | 60.1 | |
| CQL*variant=tuned/reproduced2025.12 | 43.1 | |
| MBOP2026.03 | 41 | |
| BOSA2025.12 | 40.3 | |
| OTDF2025.12 | 40.3 | |
| IGDF2025.12 | 33 |