Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continual Reinforcement Learning on HumanoidBench CRL
Loading...
53
Mean Score
SPHERE
-1.7456
12.4672
26.68
40.8928
May 6, 2026
Mean Score
Std Dev
IQM Score
IQR
Updated 27d ago
Evaluation Results
Method
Method
Links
Mean Score
Std Dev
IQM Score
IQR
SPHERE
2026.05
53
0.07
52
0.11
Top-K MoE
2026.05
36
0.05
36
0.05
SPHERE
PPO setting=matched To...
2026.05
0.54
-
-
-
Spectral Regularization
PPO setting=matched To...
2026.05
0.48
-
-
-
Spectral Normalization
PPO setting=matched To...
2026.05
0.41
-
-
-
ReDo
PPO setting=matched To...
2026.05
0.41
-
-
-
Top-K MoE
PPO setting=matched To...
2026.05
0.36
-
-
-
Feedback
Search any
task
Search any
task