Continuous Control on MuJoCo HalfCheetah H=10
260Normalized ReturnMAX-RETURN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAX-RETURNOptimizer=SAC2022.06 | 260 | |
| IPWOptimizer=SAC2022.06 | 160 | |
| SCIGANOptimizer=SAC2022.06 | 120 | |
| GALILEOOptimizer=SAC2022.06 | 70 | |
| OFF-SLOptimizer=SAC2022.06 | 40 |