Offline Reinforcement Learning on D4RL MuJoCo Walker2d medium standard
92.5Normalized ScoreEDAC
Evaluation results
| Method | Links | |
|---|---|---|
| EDACLearning Approach=Model-Free2024.02 | 92.5 | |
| MOBILELearning Approach=Model-Based2024.02 | 87.7 | |
| RAVLLearning Approach=Model-Based2024.02 | 86.3 | |
| RAMBOLearning Approach=Model-Based2024.02 | 84.9 | |
| MOPOLearning Approach=Model-Based2024.02 | 84.1 | |
| COMBOLearning Approach=Model-Based2024.02 | 81.9 | |
| CQLLearning Approach=Model-Free2024.02 | 79.5 | |
| BCLearning Approach=Model-Free2024.02 | 70.9 |