Continuous Control on MuJoCo HalfCheetah fixed random adversary L=0.1
8,805Average ReturnOracle TC-M2TD3
Evaluation Results
| Method | Links | |
|---|---|---|
| Oracle TC-M2TD3Oracle=true, Time-Constrained=true2024.06 | 8,805 | |
| Oracle TC-RARLOracle=true, Time-Constrained=true2024.06 | 8,727 | |
| TC-M2TD3Time-Constrained=true2024.06 | 7,530 | |
| Stacked TC-M2TD3Stacked=true, Time-Constrained=true2024.06 | 7,400 | |
| DR2024.06 | 6,048 | |
| Stacked TC-RARLStacked=true, Time-Constrained=true2024.06 | 5,992 | |
| TC-RARLTime-Constrained=true2024.06 | 5,751 | |
| Oracle M2TD3Oracle=true2024.06 | 4,445 | |
| M2TD32024.06 | 4,180 | |
| TD32024.06 | 2,028 | |
| RARL2024.06 | 240 | |
| Oracle RARLOracle=true2024.06 | -51 |