Continuous Control on MuJoCo HumanoidStandup fixed random adversary L=0.1
129,599Average PerformanceTC-M2TD3
Evaluation Results
| Method | Links | |
|---|---|---|
| TC-M2TD3Time-Constrained=true2024.06 | 129,599 | |
| Oracle M2TD3Oracle=true2024.06 | 118,861 | |
| Oracle TC-M2TD3Oracle=true, Time-Constrained=true2024.06 | 116,791 | |
| Oracle TC-RARLOracle=true, Time-Constrained=true2024.06 | 107,733 | |
| M2TD32024.06 | 107,692 | |
| Stacked TC-RARLStacked=true, Time-Constrained=true2024.06 | 106,213 | |
| DR2024.06 | 105,677 | |
| TC-RARLTime-Constrained=true2024.06 | 105,144 | |
| RARL2024.06 | 103,583 | |
| TD32024.06 | 91,205 | |
| Stacked TC-M2TD3Stacked=true, Time-Constrained=true2024.06 | 88,436 | |
| Oracle RARLOracle=true2024.06 | 81,583 |