Policy Optimization on MuJoCo Walker2d H=20
60.7ReturnMAX-RETURN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAX-RETURNHorizon=20, Optimization Algorithm=SAC2022.06 | 60.7 | |
| GALILEOHorizon=20, Optimization Algorithm=SAC2022.06 | 29.9 | |
| OFF-SLHorizon=20, Optimization Algorithm=SAC2022.06 | 20.1 | |
| SCIGANHorizon=20, Optimization Algorithm=SAC2022.06 | 9.1 | |
| IPWHorizon=20, Optimization Algorithm=SAC2022.06 | 2.3 |