ResearchDatasetsMVEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSequential Decision MakingMVE-S tail mean over the last 200 iterations0.307Reward3Fairness-constrained closed-loop learningMVE-S—Primary metric0