Offline Reinforcement Learning on D4RL MuJoCo Walker2d medexp standard
115.5Normalized ScoreRAVL
Evaluation Results
| Method | Links | |
|---|---|---|
| RAVLLearning Approach=Model-Based2024.02 | 115.5 | |
| MOBILELearning Approach=Model-Based2024.02 | 115.2 | |
| EDACLearning Approach=Model-Free2024.02 | 114.7 | |
| MOPOLearning Approach=Model-Based2024.02 | 112.9 | |
| CQLLearning Approach=Model-Free2024.02 | 109.1 | |
| COMBOLearning Approach=Model-Based2024.02 | 103.3 | |
| BCLearning Approach=Model-Free2024.02 | 90.1 | |
| RAMBOLearning Approach=Model-Based2024.02 | 56.7 |