Reinforcement Learning on NeoRL hopper medium
70.3Normalized ScoreTD3+BC
Evaluation results
| Method | Links | |
|---|---|---|
| TD3+BCLearning Mode=Offline, Seeds=52024.05 | 70.3 | |
| CQLLearning Mode=Offline, Seeds=52024.05 | 64.5 | |
| ADMPO-OFFLearning Mode=Offline, Seeds=52024.05 | 51.5 | |
| BCLearning Mode=Offline, Seeds=52024.05 | 51.3 | |
| MOBILELearning Mode=Offline, Seeds=52024.05 | 51.1 | |
| EDACLearning Mode=Offline, Seeds=52024.05 | 44.9 | |
| MOPOLearning Mode=Offline, Seeds=52024.05 | 1 |