Offline Reinforcement Learning on D4RL Kitchen-mixed v0 (test)
67.5Normalized ScoreD-MPC
Evaluation results
| Method | Links | |
|---|---|---|
| D-MPC2025.12 | 67.5 | |
| MPDiffuser+Rankranking=true2025.12 | 66.9 | |
| MPDiffuserranking=false2025.12 | 66.1 | |
| Decision Diffuser2025.12 | 65 | |
| A2PO2024.03 | 64.2 | |
| Diffusion-QL2024.03 | 62.6 | |
| LAPO2024.03 | 62.4 | |
| Planner2025.12 | 57.2 | |
| EQL2024.03 | 55.6 | |
| BC2025.12 | 51.5 | |
| CQL2024.03 | 51 | |
| IQL2024.03 | 51 | |
| CQL+AW2024.03 | 50.5 | |
| BC2024.03 | 47.5 | |
| MOPO2024.03 | 17.3 | |
| BCQ2024.03 | 10.6 | |
| TD3+BC2024.03 | 0.8 | |
| AWAC2024.03 | 0 |