Offline Reinforcement Learning on MuJoCo hopper-medium-expert D4RL
111.8Normalized ReturnSQL
Evaluation Results
| Method | Links | |
|---|---|---|
| SQLMethod Category=Value-Based2024.02 | 111.8 | |
| CGDTMethod Category=Combined Method2024.02 | 111.5 | |
| DCMethod Category=RCSL2024.02 | 110.4 | |
| QCS-RMethod Category=Ours2024.02 | 110.2 | |
| DTMethod Category=RCSL2024.02 | 107.6 | |
| EDTMethod Category=Combined Method2024.02 | 107.6 | |
| CQLMethod Category=Value-Based2024.02 | 105.4 | |
| RvS-RMethod Category=RCSL2024.02 | 101.7 | |
| TD3+BCMethod Category=Value-Based2024.02 | 98 | |
| IQLMethod Category=Value-Based2024.02 | 91.5 | |
| ACTMethod Category=Combined Method2024.02 | 90 |