Offline Reinforcement Learning on D4RL MuJoCo walker2d medium v2
95.5Normalized ScoreCBOP
Evaluation results
| Method | Links | |
|---|---|---|
| CBOP2024.05 | 95.5 | |
| ROMItraining steps=1M, seeds=5, version=v22026.03 | 93.6 | |
| ADMPO-OFF2024.05 | 93.2 | |
| EDAC2024.05 | 92.5 | |
| MOBILEtraining steps=1M, seeds=5, version=v22026.03 | 90.7 | |
| COUNTtraining steps=1M, seeds=5, version=v22026.03 | 88.4 | |
| MOBILE2024.05 | 87.7 | |
| RAMBO2024.05 | 84.9 | |
| MOPO2024.05 | 84.1 | |
| RAMBOtraining steps=1M, seeds=5, version=v22026.03 | 83.9 | |
| TD3+BC2024.05 | 83.7 | |
| MOPOtraining steps=1M, seeds=5, version=v22026.03 | 82.1 | |
| COMBO2024.05 | 81.9 | |
| CQL2024.05 | 79.5 | |
| CQLtraining steps=1M, seeds=5, version=v22026.03 | 73.4 | |
| BC2024.05 | 70.9 | |
| IQLtraining steps=1M, seeds=5, version=v22026.03 | 67.2 |