Offline Reinforcement Learning on D4RL Kitchen kitchen-partial v0 (test)
75.8Normalized ScoreA2PO
Evaluation results
| Method | Links | |
|---|---|---|
| A2PO2024.03 | 75.8 | |
| EQL2024.03 | 74.5 | |
| MPDiffuser+Rankranking=true2025.12 | 73.8 | |
| D-MPC2025.12 | 73.3 | |
| MPDiffuserranking=false2025.12 | 67.9 | |
| Diffusion-QL2024.03 | 60.5 | |
| Planner2025.12 | 57.2 | |
| Decision Diffuser2025.12 | 57 | |
| LAPO2024.03 | 53.7 | |
| CQL2024.03 | 49.8 | |
| IQL2024.03 | 46.3 | |
| BC2025.12 | 38 | |
| CQL+AW2024.03 | 36 | |
| BC2024.03 | 33.8 | |
| BCQ2024.03 | 18.9 | |
| MOPO2024.03 | 6.7 | |
| AWAC2024.03 | 0.3 | |
| TD3+BC2024.03 | 0 |