Reinforcement Learning on MuJoCo Walker (test)
4,888Average PerformanceStacked TC-M2TD3
Evaluation Results
| Method | Links | |
|---|---|---|
| Stacked TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 4,888 | |
| TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 4,611 | |
| Oracle TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 4,464 | |
| Oracle TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 4,442 | |
| M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 4,126 | |
| DRAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 3,851 | |
| Stacked TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 3,848 | |
| Oracle M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 3,589 | |
| TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 3,548 | |
| TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 2,020 | |
| RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,689 | |
| Oracle RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,593 |