Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning Control on DMControl cheetah-run
Loading...
838
Return
Clean
371.04
492.27
613.5
734.73
Jun 17, 2026
Return
Delta Mean Ref (%)
Delta Mean (%)
Delta Deviation (%)
Delta Deviation Ref (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Return
Delta Mean Ref (%)
Delta Mean (%)
Delta Deviation (%)
Delta Deviation Ref (%)
Clean
2026.06
838
2.6
-
-
-
SWAAP (Random)
alpha=0.9, rp=0.1
2026.06
830
-
2.5
3.2
-
SWAAP
alpha=0.9, rp=0.1
2026.06
806
-
3.6
3.4
2.8
Direct Model Poisoning
2026.06
389
-
10.4
-
-
Feedback
Search any
task
Search any
task