Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Training Efficiency on Humanoid Locomotion Simulation
Loading...
24.3
Progress Score (30 min)
Baseline RL
11.3
14.675
18.05
21.425
Jun 4, 2026
Progress Score (30 min)
Progress Score (45 min)
Progress Score (1 hr)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Progress Score (30 min)
Progress Score (45 min)
Progress Score (1 hr)
Baseline RL
Reward Method=Baseline RL
2026.06
24.3
52.6
63.7
OGMP
Reward Method=OGMP
2026.06
22.9
26.7
33
MPC-RL (Averaged)
Reward Method=MPC-RL,...
2026.06
21.9
28.2
71.5
MPC-RL (Next-step)
Reward Method=MPC-RL,...
2026.06
18.7
25
68.7
MPC-RL (Tapered)
Reward Method=MPC-RL,...
2026.06
16.7
60
77.7
CLF-RL
Reward Method=CLF-RL
2026.06
11.8
18.9
54.9
Feedback
Search any
task
Search any
task