Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Control Task on Inverted Pendulum (test)
Loading...
996.35
Average Reward
PPO
125.3604
351.4827
577.605
803.7273
Feb 5, 2026
Average Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Reward
PPO
VRER=true
2026.02
996.35
PPO
VRER=false
2026.02
977.48
TRPO
VRER=true
2026.02
962.76
TRPO
VRER=false
2026.02
916.39
A2C
VRER=true
2026.02
737.22
A2C
VRER=false
2026.02
158.86
Feedback
Search any
task
Search any
task
