List your company

Reinforcement Learning on MuJoCo HumanoidStandup

130,892Average PerformanceTC-M2TD3
71,844.9687,174.48102,504117,833.52Jun 12, 2024

Evaluation results

MethodLinks
TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06130,892
Vanilla-TC M2TD3Evaluation Protocol=Raw static average case, Seeds=102024.06130,305.38
Oracle M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06119,813
Oracle-TC M2TD3Evaluation Protocol=Raw static average case, Seeds=102024.06119,737.21
Oracle M2TD3Evaluation Protocol=Raw static average case, Seeds=102024.06118,273.54
Oracle TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06115,506
DREvaluation Protocol=Raw static average case, Seeds=102024.06110,939.89
Stacked TC RARLEvaluation Protocol=Raw static average case, Seeds=102024.06110,843.2
Oracle TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06110,535
M2TD3Evaluation Protocol=Raw static average case, Seeds=102024.06109,598.43
DRAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06109,227
Vanilla-TC RARLEvaluation Protocol=Raw static average case, Seeds=102024.06108,635.71
M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06108,136
Stacked TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06105,696
RARLEvaluation Protocol=Raw static average case, Seeds=102024.06104,764.87
Oracle-TC RARLEvaluation Protocol=Raw static average case, Seeds=102024.06104,348.01
RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06103,366
TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.06102,864
VanillaEvaluation Protocol=Raw static average case, Seeds=102024.06100,533
TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.0694,352
Stacked TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.0688,157
Stacked TC M2TD3Evaluation Protocol=Raw static average case, Seeds=102024.0688,039.74
Oracle RARLEvaluation Protocol=Raw static average case, Seeds=102024.0676,920.58
Oracle RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.0674,116