FOL
Benchmarks
TaskDatasetSOTA resultTrendResults
FOL Uniform reward
227.48Max LR
6
FOL Sine-trend rewards Horizon Generalization [T=15 -> T=25] 1.0
40.62Max LR
3
FOL Gaussian rewards, Horizon Generalization [T=15 -> T=25] 1.0
57.36Max LR
3
FOL Sine-trend reward
186.81Max LR Value
3
FOL Gaussian reward
137.19Max LR
3