Offline Reinforcement Learning on MuJoCo hopper-medium 1M
100.2Performance ScoreCOMBO
Evaluation Results
| Method | Links | |
|---|---|---|
| COMBOselection=best-epoch2025.02 | 100.2 | |
| IQLselection=best-epoch2025.02 | 95.4 | |
| MOPOselection=best-epoch2025.02 | 93.1 | |
| CQLselection=best-epoch2025.02 | 89.3 | |
| COMBO2025.02 | 84.7 | |
| TD3BCselection=best-epoch2025.02 | 77 | |
| IQL2025.02 | 65.7 | |
| MOPO2025.02 | 62.8 | |
| IOselection=best-epoch2025.02 | 60.8 | |
| TD3BC2025.02 | 60.8 | |
| CQL2025.02 | 59.1 | |
| IO2025.02 | 51.7 | |
| Dataset2025.02 | 44.3 |