List your company

Reinforcement Learning on MuJoCo Ant (test)

7,586Average RewardOracle TC-M2TD3
1,937.38563,403.85284,870.326,336.7872Jun 12, 2024Oct 12, 2024Feb 11, 2025Jun 13, 2025Oct 13, 2025Feb 12, 2026Jun 15, 2026

Evaluation results

MethodLinks
Oracle TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.067,586
Oracle TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.067,522
TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.067,124
DRAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.066,975
Stacked TC-RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.066,510
TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.066,350
Stacked TC-M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.066,269
Oracle M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.065,528
M2TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.065,330
Oracle RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.064,550
RARLAdversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.064,153
TD3Adversary Type=time-constrained fixed cosine, Radius (L)=0.1, Number of seeds=102024.064,025
DRTraining Timesteps=5 x 10^72026.062,740.69
GERS2026.062,565.73
BasePPOTraining Timesteps=3 x 10^72026.062,154.64