Continuous Control on MuJoCo Walker2d (H=10)
14.9Normalized ReturnMAX-RETURN
Evaluation results
| Method | Links | |
|---|---|---|
| MAX-RETURNOptimizer=SAC2022.06 | 14.9 | |
| MAX-RETURNHorizon=10, Optimization Algorithm=SAC2022.06 | 14.9 | |
| GALILEOOptimizer=SAC2022.06 | 11.7 | |
| GALILEOHorizon=10, Optimization Algorithm=SAC2022.06 | 11.7 | |
| OFF-SLOptimizer=SAC2022.06 | 10.7 | |
| OFF-SLHorizon=10, Optimization Algorithm=SAC2022.06 | 10.7 | |
| SCIGANOptimizer=SAC2022.06 | 8.4 | |
| SCIGANHorizon=10, Optimization Algorithm=SAC2022.06 | 8.4 | |
| IPWOptimizer=SAC2022.06 | 4.7 | |
| IPWHorizon=10, Optimization Algorithm=SAC2022.06 | 4.7 |