Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Inverse Reinforcement Learning on Half Cheetah (Normalized performance)
Loading...
83
Normalized Performance
TRIRL
5
25.25
45.5
65.75
May 10, 2026
Normalized Performance
Updated 21d ago
Evaluation Results
Method
Method
Links
Normalized Performance
TRIRL
Phase=Training
2026.05
83
TRIRL
Phase=Retraining
2026.05
70
AIRL
Phase=Training
2026.05
39
NEAR
Phase=Training
2026.05
9
NEAR
Phase=Retraining
2026.05
9
AIRL
Phase=Retraining
2026.05
8
Feedback
Search any
task
Search any
task
