Offline Reinforcement Learning on D4RL antmaze-large (diverse)
88Normalized ScoreFAC
Evaluation Results
| Method | Links | |
|---|---|---|
| FACPolicy Type=Flow, Seeds=82026.02 | 88 | |
| FQLPolicy Type=Flow, Seeds=82026.02 | 83 | |
| SAGEMethod Category=Diffusion Planners2026.03 | 77 | |
| DV*Method Category=Diffusion Planners2026.03 | 76 | |
| DQL*Method Category=Diffusion Policies2026.03 | 70.6 | |
| IDQLPolicy Type=Diffusion, Seeds=82026.02 | 67.9 | |
| IDQL*Method Category=Diffusion Policies2026.03 | 67.9 | |
| CQLMethod Category=Non-Diffusion2026.03 | 61.2 | |
| LDCQMethod Category=Diffusion Planners2026.03 | 57.7 | |
| ReBRACPolicy Type=Gaussian, Seeds=82026.02 | 54.4 | |
| SRPOPolicy Type=Diffusion, Seeds=82026.02 | 53.6 | |
| IQLPolicy Type=Gaussian, Seeds=82026.02 | 47.5 | |
| IQLMethod Category=Non-Diffusion2026.03 | 47.5 | |
| SAC-RNDPolicy Type=Gaussian, Seeds=82026.02 | 45.7 | |
| ROMI-BCQ2021.10 | 41.2 | |
| LoMAPMethod Category=Diffusion Planners2026.03 | 39.3 | |
| EPQPolicy Type=Gaussian, Seeds=82026.02 | 36.7 | |
| QIPO-OTPolicy Type=Diffusion, Seeds=82026.02 | 32.1 | |
| ROMI-CQL2021.10 | 31.4 | |
| Diffuser*Method Category=Diffusion Planners2026.03 | 27.3 | |
| BiTrajDiffAlgorithm=CQL, Augmentation Method=Ours2025.06 | 16 | |
| CQLPolicy Type=Gaussian, Seeds=82026.02 | 14.9 | |
| SyntherAlgorithm=CQL, Augmentation Method=Synther2025.06 | 12.6 | |
| BaseAlgorithm=CQL, Augmentation Method=Base2025.06 | 8 | |
| MCQPolicy Type=Gaussian, Seeds=82026.02 | 7.5 | |
| RTDiffAlgorithm=CQL, Augmentation Method=RTDiff2025.06 | 5.3 | |
| DiffStitchAlgorithm=CQL, Augmentation Method=DiffStitch2025.06 | 2.6 | |
| BCQMethod Category=Non-Diffusion2026.03 | 2.2 | |
| BAIL2021.10 | 1 | |
| DiffStitchAlgorithm=DT, Augmentation Method=DiffStitch2025.06 | 0.8 | |
| BC2021.10 | 0 | |
| BCQ2021.10 | 0 | |
| CQL2021.10 | 0 | |
| BEAR2021.10 | 0 | |
| BRAC-P2021.10 | 0 | |
| BRAC-v2021.10 | 0 | |
| MOPO2021.10 | 0 | |
| MOREL2021.10 | 0 | |
| Repb-SDE2021.10 | 0 | |
| COMBO2021.10 | 0 | |
| TD3+BCPolicy Type=Gaussian, Seeds=82026.02 | 0 | |
| CACPolicy Type=Diffusion, Seeds=82026.02 | 0 | |
| BCMethod Category=IL2026.03 | 0 | |
| BaseAlgorithm=DT, Augmentation Method=Base2025.06 | 0 | |
| RTDiffAlgorithm=DT, Augmentation Method=RTDiff2025.06 | 0 | |
| SyntherAlgorithm=DT, Augmentation Method=Synther2025.06 | 0 | |
| BiTrajDiffAlgorithm=DT, Augmentation Method=Ours2025.06 | 0 |