Offline Reinforcement Learning on MuJoCo walker2d-medium 10K
76.3ScoreCOMBO
Evaluation Results
| Method | Links | |
|---|---|---|
| COMBOselection=best-epoch2025.02 | 76.3 | |
| IQLselection=best-epoch2025.02 | 73.9 | |
| IOselection=best-epoch2025.02 | 72.1 | |
| CQLselection=best-epoch2025.02 | 67.8 | |
| Dataset2025.02 | 65.9 | |
| IQL2025.02 | 54.4 | |
| CQL2025.02 | 51 | |
| IO2025.02 | 42.2 | |
| COMBO2025.02 | 40.7 | |
| MOPOselection=best-epoch2025.02 | 16.9 | |
| TD3BCselection=best-epoch2025.02 | 5.4 | |
| MOPO2025.02 | 5 | |
| TD3BC2025.02 | 1.1 |