Policy Optimization on MuJoCo HalfCheetah H=10
2.8ReturnOFF-SL
Evaluation Results
| Method | Links | |
|---|---|---|
| OFF-SLHorizon=10, Optimization Algorithm=SAC2022.06 | 2.8 | |
| MAX-RETURNHorizon=10, Optimization Algorithm=SAC2022.06 | 2.6 | |
| SCIGANHorizon=10, Optimization Algorithm=SAC2022.06 | 1.2 | |
| GALILEOHorizon=10, Optimization Algorithm=SAC2022.06 | 0.7 | |
| IPWHorizon=10, Optimization Algorithm=SAC2022.06 | 0.4 |