ResearchDatasetsSine reward functionSine reward functionFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsRegret MinimizationSine reward function synthetic (test)289.86Oracle Regret9Regret MinimizationSine reward function weak adversaries Appendix A.7 (test)280.62Oracle Regret9