Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning Control on MyoSuite pen-twirl-hard
Loading...
3,574
Return
Clean
2,709.76
2,934.13
3,158.5
3,382.87
Jun 17, 2026
Return
Delta M Ref
Delta M
Delta D
Delta D Ref
Updated 1mo ago
Evaluation Results
Method
Method
Links
Return
Delta M Ref
Delta M
Delta D
Delta D Ref
Clean
2026.06
3,574
0.057
-
-
-
SWAAP (Random)
alpha=0.9, rp=0.1
2026.06
3,024
-
0.079
0.056
-
SWAAP
alpha=0.9, rp=0.1
2026.06
2,771
-
0.101
0.056
0.056
Direct Model Poisoning
2026.06
2,743
-
0.073
-
-
Feedback
Search any
task
Search any
task