ResearchDatasetsTriangle reward functionTriangle reward functionFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsRegret MinimizationTriangle reward function synthetic (test)366.58Oracle Regret9Regret MinimizationTriangle reward function weak adversaries Appendix A.7 (test)366.58Oracle Regret/Score9
Regret MinimizationTriangle reward function weak adversaries Appendix A.7 (test)366.58Oracle Regret/Score9