Continuous Control on MuJoCo Walker2d (H=20)
60.7Normalized ReturnMAX-RETURN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAX-RETURNOptimizer=SAC2022.06 | 60.7 | |
| GALILEOOptimizer=SAC2022.06 | 29.9 | |
| OFF-SLOptimizer=SAC2022.06 | 20.1 | |
| SCIGANOptimizer=SAC2022.06 | 9.1 | |
| IPWOptimizer=SAC2022.06 | 2.8 |