Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Ninja on Procgen easy
Loading...
7.07
Mean Episode Return
TRPO-KL
4.158
4.914
5.67
6.426
Feb 6, 2026
Mean Episode Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
Mean Episode Return
TRPO-KL
Training steps=25M, Di...
2026.02
7.07
PPO
Training steps=25M, Di...
2026.02
6.27
BPPO
Training steps=25M, Di...
2026.02
6.27
BTRPO-BC
Training steps=25M, Di...
2026.02
4.27
Feedback
Search any
task
Search any
task