Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on FailureBench Fragile Push Wall
Loading...
3,220.12
Avg Return
FARL
-1,163.1368
-25.1759
1,112.785
2,250.7459
Jan 12, 2026
Avg Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
Avg Return
FARL
mode=fine-tuning, init...
2026.01
3,220.12
PPO-Lag
mode=fine-tuning, init...
2026.01
268.83
P3O
mode=fine-tuning, init...
2026.01
-278.62
CPO
mode=fine-tuning, init...
2026.01
-994.55
Feedback
Search any
task
Search any
task
