ResearchBenchmarksSequential Decision Making on 50 simulated datasets (T=20)Follow3.54Mean RegretSUPER3.45444.03224.615.1878Sep 29, 2022Evaluation ResultsMethodMethodLinksMean RegretStandard DeviationSUPERPolicy Class=SUPER, n=...Policy Class=SUPER, n=20002022.093.540.281COMMONPolicy Class=COMMON, n...Policy Class=COMMON, n=20002022.095.680.327