FOL
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Horizon Generalization | FOL Uniform reward | Max LR227.48 | 6 | |
| Full-Information Online Learning | FOL Sine-trend rewards Horizon Generalization [T=15 -> T=25] 1.0 | Max LR40.62 | 3 | |
| Full-Information Online Learning | FOL Gaussian rewards, Horizon Generalization [T=15 -> T=25] 1.0 | Max LR57.36 | 3 | |
| Horizon Generalization | FOL Sine-trend reward | Max LR Value186.81 | 3 | |
| Horizon Generalization | FOL Gaussian reward | Max LR137.19 | 3 |
Showing 5 of 5 rows