ResearchDatasetsl2rpnFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPower Grid Controll2rpn case14 sandbox held-out (val)158,437Total steps4Power Grid Managementl2rpn sandbox stress mode Case14 (test)50.35Average Steps3