ResearchDatasetsIllustrative SettingFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReward MaximizationIllustrative Setting Novelty-seeking reward maximization452.5SQ_beta4Risk-averse reward maximizationIllustrative Setting—Primary metric0