Offline Reinforcement Learning on D4RL MuJoCo Halfcheetah standard (medium)
78.7Normalized ScoreRAVL
Evaluation Results
| Method | Links | |
|---|---|---|
| RAVLLearning Approach=Model-Based2024.02 | 78.7 | |
| RAMBOLearning Approach=Model-Based2024.02 | 77.9 | |
| MOBILELearning Approach=Model-Based2024.02 | 74.6 | |
| MOPOLearning Approach=Model-Based2024.02 | 73 | |
| EDACLearning Approach=Model-Free2024.02 | 65.9 | |
| COMBOLearning Approach=Model-Based2024.02 | 54.2 | |
| CQLLearning Approach=Model-Free2024.02 | 46.9 | |
| BCLearning Approach=Model-Free2024.02 | 43.2 |