Reinforcement Learning on MuJoCo Hopper (test)
1,946Average RewardOracle TC-M2TD3
Evaluation Results
| Method | Links | |
|---|---|---|
| Oracle TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,946 | |
| Oracle TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,735 | |
| Stacked TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,734 | |
| Stacked TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,519 | |
| TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,413 | |
| TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,317 | |
| TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,172 | |
| DRAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,091 | |
| Oracle M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 1,016 | |
| M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 938 | |
| Oracle RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 371 | |
| RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06 | 363 |