Offline Reinforcement Learning on D4RL MuJoCo Hopper standard (random)
31.9Normalized ScoreMOBILE
Evaluation Results
| Method | Links | |
|---|---|---|
| MOBILELearning Approach=Model-Based2024.02 | 31.9 | |
| MOPOLearning Approach=Model-Based2024.02 | 31.7 | |
| RAVLLearning Approach=Model-Based2024.02 | 31.4 | |
| RAMBOLearning Approach=Model-Based2024.02 | 25.4 | |
| EDACLearning Approach=Model-Free2024.02 | 25.3 | |
| COMBOLearning Approach=Model-Based2024.02 | 17.9 | |
| CQLLearning Approach=Model-Free2024.02 | 5.3 | |
| BCLearning Approach=Model-Free2024.02 | 3.7 |