Offline Reinforcement Learning on D4RL MuJoCo Halfcheetah standard (mixed)
74.9Normalized ScoreRAVL
Evaluation Results
| Method | Links | |
|---|---|---|
| RAVLLearning Approach=Model-Based2024.02 | 74.9 | |
| MOPOLearning Approach=Model-Based2024.02 | 72.1 | |
| MOBILELearning Approach=Model-Based2024.02 | 71.7 | |
| RAMBOLearning Approach=Model-Based2024.02 | 68.7 | |
| EDACLearning Approach=Model-Free2024.02 | 61.3 | |
| COMBOLearning Approach=Model-Based2024.02 | 55.1 | |
| CQLLearning Approach=Model-Free2024.02 | 45.3 | |
| BCLearning Approach=Model-Free2024.02 | 37.6 |