Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Horizon Generalization on FOL Gaussian reward
Loading...
137.19
Max LR
Gemma-2-9b-it
46.2004
69.8227
93.445
117.0673
Nov 6, 2025
Max LR
Avg LR
Beta
Updated 2d ago
Evaluation Results
Method
Method
Links
Max LR
Avg LR
Beta
Gemma-2-9b-it
Horizon Shift=T=25 to...
2025.11
137.19
20.62
0.87
Trained Gemma-2-9b-it
Horizon Shift=T=25 to...
2025.11
93.08
20.45
0.8
FTRL
Horizon Shift=T=25 to...
2025.11
49.7
27.99
0.81
Feedback
Search any
task
Search any
task