Offline Reinforcement Learning on D4RL MuJoCo Halfcheetah standard (random)
39.5Normalized ScoreRAMBO
Evaluation Results
| Method | Links | |
|---|---|---|
| RAMBOLearning Approach=Model-Based2024.02 | 39.5 | |
| MOBILELearning Approach=Model-Based2024.02 | 39.3 | |
| COMBOLearning Approach=Model-Based2024.02 | 38.8 | |
| MOPOLearning Approach=Model-Based2024.02 | 38.5 | |
| RAVLLearning Approach=Model-Based2024.02 | 34.4 | |
| CQLLearning Approach=Model-Free2024.02 | 31.3 | |
| EDACLearning Approach=Model-Free2024.02 | 28.4 | |
| BCLearning Approach=Model-Free2024.02 | 2.2 |