Offline Reinforcement Learning on D4RL MuJoCo hopper random v2
53.6Normalized ScoreMOReL
Evaluation results
| Method | Links | |
|---|---|---|
| MOReL2025.04 | 53.6 | |
| VIPO-MOBILE2025.04 | 33.4 | |
| ADMPO-OFF2024.05 | 32.7 | |
| MOBILE2024.05 | 31.9 | |
| MOBILE2025.04 | 31.9 | |
| MOPO2024.05 | 31.7 | |
| ROMItraining steps=1M, seeds=5, version=v22026.03 | 31.7 | |
| MOPO*Retrained on v2=true2025.04 | 31.7 | |
| CBOP2024.05 | 31.4 | |
| VIPO-MOPO2025.04 | 30.2 | |
| COUNTtraining steps=1M, seeds=5, version=v22026.03 | 30 | |
| MOBILEtraining steps=1M, seeds=5, version=v22026.03 | 28.5 | |
| MOPOtraining steps=1M, seeds=5, version=v22026.03 | 27.8 | |
| RAMBO2024.05 | 25.4 | |
| RAMBO2025.04 | 25.4 | |
| EDAC2024.05 | 25.3 | |
| RAMBOtraining steps=1M, seeds=5, version=v22026.03 | 23.9 | |
| COMBO2024.05 | 17.9 | |
| COMBO2025.04 | 17.9 | |
| DQL2025.04 | 17.5 | |
| TD3+BC2025.04 | 11 | |
| IQL2025.04 | 10.8 | |
| TD3+BC2024.05 | 8.5 | |
| CQLtraining steps=1M, seeds=5, version=v22026.03 | 7.9 | |
| IQLtraining steps=1M, seeds=5, version=v22026.03 | 7.6 | |
| CQL2024.05 | 5.3 | |
| CQL2025.04 | 5.3 | |
| BC2024.05 | 3.7 |