Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on MuJoCo Ant (test)
Loading...
7,586
Average Reward
Oracle TC-M2TD3
1,937.3856
3,403.8528
4,870.32
6,336.7872
Jun 12, 2024
Oct 12, 2024
Feb 11, 2025
Jun 13, 2025
Oct 13, 2025
Feb 12, 2026
Jun 15, 2026
Average Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Reward
Oracle TC-M2TD3
Adversary Type=time-co...
2024.06
7,586
Oracle TC-RARL
Adversary Type=time-co...
2024.06
7,522
TC-RARL
Adversary Type=time-co...
2024.06
7,124
DR
Adversary Type=time-co...
2024.06
6,975
Stacked TC-RARL
Adversary Type=time-co...
2024.06
6,510
TC-M2TD3
Adversary Type=time-co...
2024.06
6,350
Stacked TC-M2TD3
Adversary Type=time-co...
2024.06
6,269
Oracle M2TD3
Adversary Type=time-co...
2024.06
5,528
M2TD3
Adversary Type=time-co...
2024.06
5,330
Oracle RARL
Adversary Type=time-co...
2024.06
4,550
RARL
Adversary Type=time-co...
2024.06
4,153
TD3
Adversary Type=time-co...
2024.06
4,025
DR
Training Timesteps=5 x...
2026.06
2,740.69
GERS
2026.06
2,565.73
BasePPO
Training Timesteps=3 x...
2026.06
2,154.64
Feedback
Search any
task
Search any
task