Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Horizon Generalization on FOL Gaussian reward

137.19Max LR

Gemma-2-9b-it

46.200469.822793.445117.0673Nov 6, 2025
Updated 2d ago

Evaluation Results

MethodLinks
2025.11
137.1920.620.87
2025.11
93.0820.450.8
2025.11
49.727.990.81