Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on Humanoid v4
Loading...
5,715
Reward
C-DSAC
-56.1472
1,442.1314
2,940.41
4,438.6886
Apr 26, 2026
May 5, 2026
May 15, 2026
May 24, 2026
Jun 3, 2026
Jun 12, 2026
Jun 22, 2026
Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
C-DSAC
Number of runs=100, Se...
2026.04
5,715
PPO-Clip
Number of seeds=5, Eva...
2026.06
660
per-sample PPO-KL
Number of seeds=5, Eva...
2026.06
660
Adaptive β
Number of seeds=5, Eva...
2026.06
553
DDPG-AdaGamma
Base RL Algorithm=DDPG...
2026.05
457.02
DDPG-Uncertainty
Base RL Algorithm=DDPG...
2026.05
454.46
DDPG-CrossValidate
Base RL Algorithm=DDPG...
2026.05
356.85
Fixed β
Number of seeds=5, Eva...
2026.06
342
TRPO-AdaGamma
Base RL Algorithm=TRPO...
2026.05
284.49
TRPO-Uncertainty
Base RL Algorithm=TRPO...
2026.05
250.65
TRPO-CrossValidate
Base RL Algorithm=TRPO...
2026.05
221.1
TRPO-Fixed-γ
Base RL Algorithm=TRPO...
2026.05
218.15
DDPG-Fixed-γ
Base RL Algorithm=DDPG...
2026.05
165.82
Feedback
Search any
task
Search any
task