Offline Reinforcement Learning on D4RL antmaze-large (play)
90Normalized ScoreFAC
Evaluation Results
| Method | Links | |
|---|---|---|
| FACPolicy Type=Flow, Seeds=82026.02 | 90 | |
| FQLPolicy Type=Flow, Seeds=82026.02 | 84 | |
| IDQLPolicy Type=Diffusion, Seeds=82026.02 | 63.5 | |
| ReBRACPolicy Type=Gaussian, Seeds=82026.02 | 60.4 | |
| QIPO-OTPolicy Type=Diffusion, Seeds=82026.02 | 55.5 | |
| SRPOPolicy Type=Diffusion, Seeds=82026.02 | 53.6 | |
| SAC-RNDPolicy Type=Gaussian, Seeds=82026.02 | 43.9 | |
| EPQPolicy Type=Gaussian, Seeds=82026.02 | 40 | |
| IQLPolicy Type=Gaussian, Seeds=82026.02 | 39.6 | |
| ROMI-CQL2021.10 | 23.6 | |
| ROMI-BCQ2021.10 | 20.2 | |
| CQLPolicy Type=Gaussian, Seeds=82026.02 | 15.8 | |
| MCQPolicy Type=Gaussian, Seeds=82026.02 | 2.5 | |
| BAIL2021.10 | 2.2 | |
| BFQPolicy Type=One-Step Flow/Diffusion Policy2026.06 | 0.885 | |
| OFQLPolicy Type=One-Step Flow/Diffusion Policy2026.06 | 0.84 | |
| FQLPolicy Type=One-Step Flow/Diffusion Policy2026.06 | 0.84 | |
| DQLPolicy Type=Diffusion Policy2026.06 | 0.833 | |
| SAGEMethod Category=Diffusion Planners2026.03 | 0.821 | |
| DQL*Method Category=Diffusion Policies2026.03 | 0.813 | |
| DV*Method Category=Diffusion Planners2026.03 | 0.764 | |
| IDQL*Method Category=Diffusion Policies2026.03 | 0.635 | |
| SORLPolicy Type=One-Step Flow/Diffusion Policy2026.06 | 0.573 | |
| CQLMethod Category=Non-Diffusion2026.03 | 0.537 | |
| SRPOPolicy Type=One-Step Flow/Diffusion Policy2026.06 | 0.536 | |
| IDQLPolicy Type=Diffusion Policy2026.06 | 0.487 | |
| IQLMethod Category=Non-Diffusion2026.03 | 0.396 | |
| IQLPolicy Type=Gaussian Policy2026.06 | 0.386 | |
| EDPPolicy Type=Diffusion Policy2026.06 | 0.333 | |
| LoMAPMethod Category=Diffusion Planners2026.03 | 0.207 | |
| TD3+BCPolicy Type=Gaussian, Seeds=82026.02 | 0.2 | |
| Diffuser*Method Category=Diffusion Planners2026.03 | 0.173 | |
| BCQMethod Category=Non-Diffusion2026.03 | 0.067 | |
| TD3-BCPolicy Type=Gaussian Policy2026.06 | 0.002 | |
| 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 | |
| CACPolicy Type=Diffusion, Seeds=82026.02 | 0 | |
| BCMethod Category=IL2026.03 | 0 | |
| BCPolicy Type=Gaussian Policy2026.06 | 0 |