ResearchDatasetsIllustrative SettingIllustrative SettingFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReward MaximizationIllustrative Setting Novelty-seeking reward maximization452.5SQ_beta4Risk-averse reward maximizationIllustrative Setting—Primary metric0