Reinforcement Learning on neorl halfcheetah high
84Normalized ScoreADMPO-OFF
Evaluation results
| Method | Links | |
|---|---|---|
| ADMPO-OFFLearning Mode=Offline, Seeds=52024.05 | 84 | |
| MOBILELearning Mode=Offline, Seeds=52024.05 | 83 | |
| EDACLearning Mode=Offline, Seeds=52024.05 | 81.4 | |
| CQLLearning Mode=Offline, Seeds=52024.05 | 77.4 | |
| TD3+BCLearning Mode=Offline, Seeds=52024.05 | 75.3 | |
| BCLearning Mode=Offline, Seeds=52024.05 | 71.3 | |
| MOPOLearning Mode=Offline, Seeds=52024.05 | 65.9 |