ResearchTasksFull-Information Online LearningFull-Information Online LearningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedFOL Sine-trend rewards Horizon Generalization [T=15 -> T=25] 1.0GPT-4o mini40.62Max LR3Jun 1, 2026FOL Gaussian rewards, Horizon Generalization [T=15 -> T=25] 1.0GPT-4o mini57.36Max LR3Jun 1, 2026