Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Acrobot Control on Acrobot
Loading...
100
Success Rate
PPO–MPPI
-4
23
50
77
Dec 18, 2025
Success Rate
Episode Length (Steps)
Cumulative Reward
Min Episode Steps
Updated 24d ago
Evaluation Results
Method
Method
Links
Success Rate
Episode Length (Steps)
Cumulative Reward
Min Episode Steps
PPO–MPPI
Influence ratio (ρ)=0
2025.12
100
82.6
-92.6
-
PPO–MPPI
Influence ratio (ρ)=0.3
2025.12
100
90.7
-103.1
-
PPO
2025.12
40
332.6
-347.1
-
SAC
2025.12
0
500
-500
-
ReEvo
2025.05
-
-
-
99.65
MoH
2025.05
-
-
-
88.76
Feedback
Search any
task
Search any
task
