Offline Reinforcement Learning on D4RL MuJoCo Walker2d standard (mixed)
89.9Normalized ScoreMOBILE
Evaluation Results
| Method | Links | |
|---|---|---|
| MOBILELearning Approach=Model-Based2024.02 | 89.9 | |
| RAMBOLearning Approach=Model-Based2024.02 | 89.2 | |
| EDACLearning Approach=Model-Free2024.02 | 87.1 | |
| MOPOLearning Approach=Model-Based2024.02 | 85.6 | |
| RAVLLearning Approach=Model-Based2024.02 | 83 | |
| CQLLearning Approach=Model-Free2024.02 | 76.8 | |
| COMBOLearning Approach=Model-Based2024.02 | 56 | |
| BCLearning Approach=Model-Free2024.02 | 20.3 |