Offline Reinforcement Learning on D4RL MuJoCo Hopper medexp standard
112.6Normalized ScoreMOBILE
Evaluation Results
| Method | Links | |
|---|---|---|
| MOBILELearning Approach=Model-Based2024.02 | 112.6 | |
| COMBOLearning Approach=Model-Based2024.02 | 111.1 | |
| EDACLearning Approach=Model-Free2024.02 | 110.7 | |
| RAVLLearning Approach=Model-Based2024.02 | 110.1 | |
| CQLLearning Approach=Model-Free2024.02 | 96.9 | |
| RAMBOLearning Approach=Model-Based2024.02 | 88.2 | |
| MOPOLearning Approach=Model-Based2024.02 | 81.6 | |
| BCLearning Approach=Model-Free2024.02 | 53.9 |