Continuous Control on MuJoCo HalfCheetah H=20
13.3Normalized ReturnMAX-RETURN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAX-RETURNOptimizer=SAC2022.06 | 13.3 | |
| IPWOptimizer=SAC2022.06 | 0.5 | |
| SCIGANOptimizer=SAC2022.06 | -0.3 | |
| GALILEOOptimizer=SAC2022.06 | -1.1 | |
| OFF-SLOptimizer=SAC2022.06 | -1.1 |