Policy Optimization on MuJoCo HalfCheetah H=20
13.3ReturnMAX-RETURN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAX-RETURNHorizon=20, Optimization Algorithm=SAC2022.06 | 13.3 | |
| IPWHorizon=20, Optimization Algorithm=SAC2022.06 | 0.2 | |
| SCIGANHorizon=20, Optimization Algorithm=SAC2022.06 | -0.3 | |
| GALILEOHorizon=20, Optimization Algorithm=SAC2022.06 | -1.1 | |
| OFF-SLHorizon=20, Optimization Algorithm=SAC2022.06 | -1.1 |