Offline Reinforcement Learning on MuJoCo hopper-medium (5K)
90.5ScoreIQL
Evaluation Results
| Method | Links | |
|---|---|---|
| IQLselection=best-epoch2025.02 | 90.5 | |
| IOselection=best-epoch2025.02 | 83.8 | |
| CQLselection=best-epoch2025.02 | 72.3 | |
| COMBOselection=best-epoch2025.02 | 68.4 | |
| COMBO2025.02 | 50.9 | |
| CQL2025.02 | 49 | |
| Dataset2025.02 | 47.2 | |
| IQL2025.02 | 46.8 | |
| IO2025.02 | 45.9 | |
| TD3BCselection=best-epoch2025.02 | 32.6 | |
| MOPOselection=best-epoch2025.02 | 26.2 | |
| TD3BC2025.02 | 12.5 | |
| MOPO2025.02 | 4.1 |