Policy Optimization on MuJoCo Hopper H=40
71ReturnMAX-RETURN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAX-RETURNHorizon=40, Optimization Algorithm=SAC2022.06 | 71 | |
| GALILEOHorizon=40, Optimization Algorithm=SAC2022.06 | 53.5 | |
| SCIGANHorizon=40, Optimization Algorithm=SAC2022.06 | 46.2 | |
| IPWHorizon=40, Optimization Algorithm=SAC2022.06 | 5.9 | |
| OFF-SLHorizon=40, Optimization Algorithm=SAC2022.06 | 4.6 |