ResearchBenchmarksSequential Decision Making on 50 simulated datasets T=2Sequential Decision Making on 50 simulated datasets T=2Follow0.0791Mean RegretSUPER0.0784040.0831020.08780.092498Sep 29, 2022Evaluation resultsMethodMethodLinksMean RegretStandard DeviationSUPERPolicy Class=SUPERPolicy Class=SUPER2022.090.07910.0038COMMONPolicy Class=COMMONPolicy Class=COMMON2022.090.09650.0033