Navigation on D4RL antmaze-medium-play
88.1Normalized ScoreOFQL
Evaluation Results
| Method | Links | |
|---|---|---|
| OFQLCategory=One-step Flow Policies2025.08 | 88.1 | |
| PORMethod Category=Conditioned BC, Seeds=52022.10 | 84.6 | |
| FQLCategory=One-step Flow Policies2025.08 | 78 | |
| C-LAPImplementation=Reproduced2024.11 | 77.5 | |
| DQLCategory=Multi-step Diffusion Policies2025.08 | 76.6 | |
| EDPCategory=Multi-step Diffusion Policies2025.08 | 73.3 | |
| IQLMethod Category=Weighted BC, Seeds=52022.10 | 71.2 | |
| IQLCategory=Non-Diffusion Policies2025.08 | 71.2 | |
| CQLMethod Category=Best RL Baseline, Seeds=52022.10 | 68 | |
| IDQLCategory=Multi-step Diffusion Policies2025.08 | 67.3 | |
| RvSMethod Category=Conditioned BC, Seeds=52022.10 | 58.1 | |
| TD3-BCCategory=Non-Diffusion Policies2025.08 | 10.6 | |
| DDCategory=Diffusion Planners2025.08 | 8 | |
| DiffuserCategory=Diffusion Planners2025.08 | 6.7 | |
| 10%BCMethod Category=Weighted BC, Seeds=52022.10 | 5.4 | |
| One-step RLMethod Category=Weighted BC, Seeds=52022.10 | 0.3 | |
| PLASImplementation=Original Paper2024.11 | 0.2 | |
| DTMethod Category=Conditioned BC, Seeds=52022.10 | 0 | |
| PLASImplementation=Reproduced2024.11 | 0 | |
| MOPOImplementation=Reproduced2024.11 | 0 | |
| MOBILEImplementation=Reproduced2024.11 | 0 | |
| BCCategory=Non-Diffusion Policies2025.08 | 0 |